{ "schemaVersion": 2, "asOf": "2026-10-01", "checkedOn": "2026-10-01", "currency": "USD", "unit": "per 1M tokens", "counts": { "models": 94, "offers": 213, "endpoints": 11, "regions": 80 }, "endpoints": [ { "id": "openai", "label": "OpenAI API", "kind": "direct", "vendor": "OpenAI" }, { "id": "anthropic", "label": "Anthropic API", "kind": "direct", "vendor": "Anthropic" }, { "id": "gemini", "label": "Gemini API", "kind": "direct", "vendor": "Google" }, { "id": "mistral", "label": "Mistral API", "kind": "direct", "vendor": "Mistral" }, { "id": "deepseek", "label": "DeepSeek API", "kind": "direct", "vendor": "DeepSeek" }, { "id": "xai", "label": "xAI API", "kind": "direct", "vendor": "xAI" }, { "id": "groq", "label": "Groq", "kind": "direct", "vendor": "Groq" }, { "id": "cohere", "label": "Cohere API", "kind": "direct", "vendor": "Cohere" }, { "id": "bedrock", "label": "AWS Bedrock", "kind": "cloud", "vendor": "AWS" }, { "id": "azure", "label": "Azure AI Foundry", "kind": "cloud", "vendor": "Microsoft" }, { "id": "vertex", "label": "GCP Vertex AI", "kind": "cloud", "vendor": "Google Cloud" } ], "azureProfileLabels": { "Global": "Global Standard", "DataZone": "Data Zone Standard", "Regional": "Regional Standard" }, "vertexLocationGroups": { "americas": [ "northamerica-northeast1", "southamerica-east1" ], "asia-pacific": [ "asia-east1", "asia-east2", "asia-northeast1", "asia-northeast3", "asia-south1", "asia-southeast1", "australia-southeast1" ], "europe": [ "europe-central2", "europe-north1", "europe-southwest1", "europe-west1", "europe-west2", "europe-west3", "europe-west4", "europe-west6", "europe-west8", "europe-west9" ], "middle-east": [ "me-central1", "me-central2", "me-west1" ], "united-states": [ "us-central1", "us-east1", "us-east4", "us-east5", "us-south1", "us-west1", "us-west4" ] }, "models": [ { "slug": "claude-opus-5-5", "name": "Claude Opus 5.5", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-5-5", "priceSource": "curated", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 5, "batchInput": 2, "batchOutput": 10, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-5-5", "priceSource": "curated", "input": 4.4, "inputMax": null, "output": 22, "outputMax": null, "cacheRead": 0.22, "cacheWrite": 5.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-southeast-4", "eu-west-2", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-northeast-1", "ap-northeast-3", "ap-southeast-2", "ap-southeast-4", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-5-5", "priceSource": "curated", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-5-5", "priceSource": "curated", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-opus-5", "name": "Claude Opus 5", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-5", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-5", "priceSource": "genai-prices", "input": 5.5, "inputMax": null, "output": 27.5, "outputMax": null, "cacheRead": 0.55, "cacheWrite": 6.875, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-northeast-2", "ap-southeast-4", "eu-north-1", "eu-west-1", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-south-1", "ap-south-2", "ap-southeast-2", "ap-southeast-4", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-5", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-5", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-opus-4-8", "name": "Claude Opus 4.8", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-4-8", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-4-8", "priceSource": "genai-prices", "input": 5.5, "inputMax": null, "output": 27.5, "outputMax": null, "cacheRead": 0.55, "cacheWrite": 6.875, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-southeast-4", "eu-north-1", "eu-west-1", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-northeast-1", "ap-northeast-3", "ap-southeast-2", "ap-southeast-4", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-4-8", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-4-8", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-opus-4-7", "name": "Claude Opus 4.7", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-4-7", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-4-7", "priceSource": "genai-prices", "input": 5.5, "inputMax": null, "output": 27.5, "outputMax": null, "cacheRead": 0.55, "cacheWrite": 6.875, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-southeast-4", "eu-north-1", "eu-west-1", "us-east-1" ], "geo": [ "ap-northeast-1", "ap-northeast-3", "ap-southeast-2", "ap-southeast-4", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-4-7", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-4-7", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-opus-4-6", "name": "Claude Opus 4.6", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-4-6", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-4-6-v1", "priceSource": "genai-prices", "input": 5.5, "inputMax": null, "output": 27.5, "outputMax": null, "cacheRead": 0.55, "cacheWrite": 6.875, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "eu-west-2" ], "geo": [ "ap-southeast-2", "ap-southeast-4", "ap-southeast-6", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-6.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-4-6", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-4-6", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-fable-5-1", "name": "Claude Fable 5.1", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-fable-5-1", "priceSource": "curated", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 0.25, "cacheWrite": 12.5, "batchInput": 5, "batchOutput": 25, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-fable-5-1", "priceSource": "curated", "input": 11, "inputMax": null, "output": 55, "outputMax": null, "cacheRead": 0.275, "cacheWrite": 13.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "us-gov-west-1" ], "geo": [ "ca-central-1", "ca-west-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5-1.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-fable-5-1", "priceSource": "curated", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 0.25, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-fable-5-1", "priceSource": "curated", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 0.25, "cacheWrite": 12.5, "batchInput": 5, "batchOutput": 25, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-fable-5", "name": "Claude Fable 5", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-fable-5", "priceSource": "genai-prices", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-fable-5", "priceSource": "genai-prices", "input": 11, "inputMax": null, "output": 55, "outputMax": null, "cacheRead": 1.1, "cacheWrite": 13.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "us-east-1" ], "geo": [ "ca-central-1", "ca-west-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-fable-5", "priceSource": "curated", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-fable-5", "priceSource": "genai-prices", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-sonnet-5-5", "name": "Claude Sonnet 5.5", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-sonnet-5-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": 1, "batchOutput": 5, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-5-5", "priceSource": "curated", "input": 2.2, "inputMax": null, "output": 11, "outputMax": null, "cacheRead": 0.22, "cacheWrite": 2.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "us-gov-west-1" ], "geo": [ "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-sonnet-5-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-sonnet-5-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": 1, "batchOutput": 5, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-sonnet-5", "name": "Claude Sonnet 5", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-sonnet-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": 1, "batchOutput": 5, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-5", "priceSource": "curated", "input": 2.2, "inputMax": null, "output": 11, "outputMax": null, "cacheRead": 0.22, "cacheWrite": 2.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-northeast-2", "ap-southeast-1", "ap-southeast-4", "eu-north-1", "eu-west-1", "eu-west-2", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-south-1", "ap-south-2", "ap-southeast-4", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-sonnet-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-sonnet-5", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6", "vendor": "Anthropic", "modality": "chat", "context": 1000000, "maxOutput": 64000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-sonnet-4-6", "priceSource": "genai-prices", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-4-6", "priceSource": "genai-prices", "input": 3.3, "inputMax": null, "output": 16.5, "outputMax": null, "cacheRead": 0.33, "cacheWrite": 4.125, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "eu-west-2" ], "geo": [ "ap-northeast-1", "ap-northeast-3", "ap-southeast-2", "ap-southeast-4", "ap-southeast-6", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-6.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-sonnet-4-6", "priceSource": "curated", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-sonnet-4-6", "priceSource": "curated", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-sonnet-4-5", "name": "Claude Sonnet 4.5", "vendor": "Anthropic", "modality": "chat", "context": 200000, "maxOutput": 64000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-sonnet-4-5", "priceSource": "genai-prices", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "priceSource": "genai-prices", "input": 3.3, "inputMax": null, "output": 16.5, "outputMax": null, "cacheRead": 0.33, "cacheWrite": 4.125, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [], "geo": [ "ap-northeast-1", "ap-southeast-2", "ap-southeast-4", "ap-southeast-6", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-sonnet-4-5", "priceSource": "curated", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-sonnet-4-5", "priceSource": "curated", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": 3.75, "batchInput": 1.5, "batchOutput": 7.5, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-opus-4-5", "name": "Claude Opus 4.5", "vendor": "Anthropic", "modality": "chat", "context": 200000, "maxOutput": 64000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-opus-4-5", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-4-5-20251101-v1:0", "priceSource": "genai-prices", "input": 5.5, "inputMax": null, "output": 27.5, "outputMax": null, "cacheRead": 0.55, "cacheWrite": 6.875, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [], "geo": [ "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-opus-4-5", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-opus-4-5", "priceSource": "curated", "input": 5, "inputMax": null, "output": 25, "outputMax": null, "cacheRead": 0.5, "cacheWrite": 6.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "claude-haiku-4-5", "name": "Claude Haiku 4.5", "vendor": "Anthropic", "modality": "chat", "context": 200000, "maxOutput": 64000, "offers": [ { "endpoint": "anthropic", "endpointModelId": "claude-haiku-4-5", "priceSource": "genai-prices", "input": 1, "inputMax": null, "output": 5, "outputMax": null, "cacheRead": 0.1, "cacheWrite": 1.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://www.anthropic.com/pricing#api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "priceSource": "genai-prices", "input": 1.1, "inputMax": null, "output": 5.5, "outputMax": null, "cacheRead": 0.11, "cacheWrite": 1.375, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 4 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-southeast-4", "eu-north-1", "eu-west-1", "us-east-1" ], "geo": [ "ap-northeast-1", "ap-south-1", "ap-south-2", "ap-southeast-2", "ap-southeast-4", "ap-southeast-6", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "mx-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-4-5.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "claude-haiku-4-5", "priceSource": "curated", "input": 1, "inputMax": null, "output": 5, "outputMax": null, "cacheRead": 0.1, "cacheWrite": 1.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "claude-haiku-4-5", "priceSource": "curated", "input": 1, "inputMax": null, "output": 5, "outputMax": null, "cacheRead": 0.1, "cacheWrite": 1.25, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 8192, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-6-astra", "name": "GPT-6 Astra", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-6-astra", "priceSource": "curated", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": null, "batchInput": 5, "batchOutput": 25, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-6-astra", "priceSource": "azure-retail", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 4, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 10, "inputMax": null, "output": 50, "outputMax": null, "cacheRead": 1, "cacheWrite": 12.5, "batchInput": null, "batchOutput": null, "regionCount": 27, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 11, "inputMax": 12, "output": 55, "outputMax": 60, "cacheRead": 1.1, "cacheWrite": 13.75, "batchInput": null, "batchOutput": null, "regionCount": 21, "regions": [ "australiaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-6-sol", "name": "GPT-6 Sol", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-6-sol", "priceSource": "curated", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": 1, "batchOutput": 5, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-6-sol", "priceSource": "azure-retail", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "japaneast", "koreacentral", "malaysiawest", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 9, "AP": 6, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 2, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "regionCount": 26, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "japaneast", "koreacentral", "malaysiawest", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 2.2, "inputMax": 2.4, "output": 11, "outputMax": 12, "cacheRead": 0.22, "cacheWrite": 2.75, "batchInput": null, "batchOutput": null, "regionCount": 13, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-6-luna", "name": "GPT-6 Luna", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-6-luna", "priceSource": "curated", "input": 0.1, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": 0.01, "cacheWrite": null, "batchInput": 0.05, "batchOutput": 0.25, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-6-luna", "priceSource": "azure-retail", "input": 0.1, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": 0.01, "cacheWrite": 0.125, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "japaneast", "koreacentral", "malaysiawest", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 9, "AP": 6, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.1, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": 0.01, "cacheWrite": 0.125, "batchInput": null, "batchOutput": null, "regionCount": 26, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "japaneast", "koreacentral", "malaysiawest", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.11, "inputMax": 0.12, "output": 0.55, "outputMax": 0.6, "cacheRead": 0.011, "cacheWrite": 0.1375, "batchInput": null, "batchOutput": null, "regionCount": 13, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.6-sol", "priceSource": "curated", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.4, "cacheWrite": 6.25, "batchInput": 2, "batchOutput": 10, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.6-sol", "priceSource": "azure-retail", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.4, "cacheWrite": 5, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ], "counts": { "US": 9, "EU": 9, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 4, "inputMax": null, "output": 20, "outputMax": null, "cacheRead": 0.4, "cacheWrite": 5, "batchInput": null, "batchOutput": null, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 4.4, "inputMax": 5.5, "output": 22, "outputMax": 27.5, "cacheRead": 0.44, "cacheWrite": 5.5, "batchInput": null, "batchOutput": null, "regionCount": 15, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.6-terra", "priceSource": "curated", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 3.125, "batchInput": 1, "batchOutput": 6, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.6-terra", "priceSource": "azure-retail", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ], "counts": { "US": 9, "EU": 9, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": 2.5, "batchInput": null, "batchOutput": null, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 2.2, "inputMax": 2.75, "output": 13.2, "outputMax": 16.5, "cacheRead": 0.22, "cacheWrite": 2.75, "batchInput": null, "batchOutput": null, "regionCount": 15, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "openai.gpt-5.6-terra", "priceSource": null, "input": null, "inputMax": null, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 3 }, "tiers": { "inRegion": [ "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "geo": [ "ap-south-1", "ap-south-2", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.6-luna", "priceSource": "curated", "input": 0.2, "inputMax": null, "output": 1.2, "outputMax": null, "cacheRead": 0.01, "cacheWrite": 1.25, "batchInput": 0.1, "batchOutput": 0.6, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.6-luna", "priceSource": "azure-retail", "input": 0.2, "inputMax": null, "output": 1.2, "outputMax": null, "cacheRead": 0.02, "cacheWrite": 0.25, "batchInput": null, "batchOutput": null, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ], "counts": { "US": 9, "EU": 9, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.2, "inputMax": null, "output": 1.2, "outputMax": null, "cacheRead": 0.02, "cacheWrite": 0.25, "batchInput": null, "batchOutput": null, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.22, "inputMax": 0.275, "output": 1.32, "outputMax": 1.65, "cacheRead": 0.022, "cacheWrite": 0.275, "batchInput": null, "batchOutput": null, "regionCount": 15, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "openai.gpt-5.6-luna", "priceSource": null, "input": null, "inputMax": null, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 3 }, "tiers": { "inRegion": [ "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "geo": [ "ap-south-1", "ap-south-2", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-5", "name": "GPT-5.5", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.5", "priceSource": "genai-prices", "input": 5, "inputMax": null, "output": 30, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 2.5, "batchOutput": 15, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.5", "priceSource": "azure-retail", "input": 5, "inputMax": null, "output": 30, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 2.5, "batchOutput": 15, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 9, "AP": 5 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 5, "inputMax": null, "output": 30, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 2.5, "batchOutput": 15, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 5.5, "inputMax": 6, "output": 33, "outputMax": 36, "cacheRead": 0.55, "cacheWrite": null, "batchInput": 2.75, "batchOutput": 16.5, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-5-pro", "name": "GPT-5.5 pro", "vendor": "OpenAI", "modality": "chat", "context": 1000000, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.5-pro", "priceSource": "genai-prices", "input": 30, "inputMax": null, "output": 180, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 15, "batchOutput": 90, "context": 1000000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-4", "name": "GPT-5.4", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.4", "priceSource": "genai-prices", "input": 2.5, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 7.5, "context": 1050000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.4", "priceSource": "azure-retail", "input": 2.5, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 7.5, "context": 1050000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 2.5, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 7.5, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 2.75, "inputMax": 3, "output": 16.5, "outputMax": 18, "cacheRead": 0.275, "cacheWrite": null, "batchInput": 1.375, "batchOutput": 8.25, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "openai.gpt-5.4", "priceSource": null, "input": null, "inputMax": null, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "counts": { "US": 4 }, "tiers": { "inRegion": [ "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-4-mini", "name": "GPT-5.4 mini", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.4-mini", "priceSource": "genai-prices", "input": 0.75, "inputMax": null, "output": 4.5, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 2.25, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.4-mini", "priceSource": "azure-retail", "input": 0.75, "inputMax": null, "output": 4.5, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 2.25, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.75, "inputMax": null, "output": 4.5, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 2.25, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.825, "inputMax": 0.9, "output": 4.95, "outputMax": 5.4, "cacheRead": 0.0825, "cacheWrite": null, "batchInput": 0.4125, "batchOutput": 2.475, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-4-nano", "name": "GPT-5.4 nano", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.4-nano", "priceSource": "genai-prices", "input": 0.2, "inputMax": null, "output": 1.25, "outputMax": null, "cacheRead": 0.02, "cacheWrite": null, "batchInput": 0.1, "batchOutput": 0.625, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.4-nano", "priceSource": "azure-retail", "input": 0.2, "inputMax": null, "output": 1.25, "outputMax": null, "cacheRead": 0.02, "cacheWrite": null, "batchInput": 0.1, "batchOutput": 0.625, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.2, "inputMax": null, "output": 1.25, "outputMax": null, "cacheRead": 0.02, "cacheWrite": null, "batchInput": 0.1, "batchOutput": 0.625, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.22, "inputMax": 0.24, "output": 1.375, "outputMax": 1.5, "cacheRead": 0.022, "cacheWrite": null, "batchInput": 0.11, "batchOutput": 0.6875, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-4-pro", "name": "GPT-5.4 pro", "vendor": "OpenAI", "modality": "chat", "context": 1050000, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.4-pro", "priceSource": "genai-prices", "input": 30, "inputMax": null, "output": 180, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 15, "batchOutput": 90, "context": 1050000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.4-pro", "priceSource": "azure-retail", "input": 30, "inputMax": null, "output": 180, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 15, "batchOutput": 90, "context": 1050000, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 30, "inputMax": null, "output": 180, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 15, "batchOutput": 90, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 33, "inputMax": null, "output": 198, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 16.5, "batchOutput": 99, "regionCount": 14, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-3-codex", "name": "GPT-5.3 Codex", "vendor": "OpenAI", "modality": "chat", "context": 400000, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.3-codex", "priceSource": "genai-prices", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 400000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.3-codex", "priceSource": "azure-retail", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 400000, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 9, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 1.925, "inputMax": 2.1, "output": 15.4, "outputMax": 16.8, "cacheRead": 0.1925, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-2", "name": "GPT-5.2", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.2", "priceSource": "genai-prices", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.2", "priceSource": "azure-retail", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": 0.875, "batchOutput": 7, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 1.75, "inputMax": null, "output": 14, "outputMax": null, "cacheRead": 0.175, "cacheWrite": null, "batchInput": 0.875, "batchOutput": 7, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 1.925, "inputMax": 2.1, "output": 15.4, "outputMax": 16.8, "cacheRead": 0.1925, "cacheWrite": null, "batchInput": 0.9625, "batchOutput": 7.7, "regionCount": 22, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-2-pro", "name": "GPT-5.2 pro", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.2-pro", "priceSource": "genai-prices", "input": 21, "inputMax": null, "output": 168, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 10.5, "batchOutput": 84, "context": 272000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.2-pro", "priceSource": "azure-retail", "input": 21, "inputMax": null, "output": 168, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 10.5, "batchOutput": 84, "context": 272000, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 9, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 21, "inputMax": null, "output": 168, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 10.5, "batchOutput": 84, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 23.1, "inputMax": null, "output": 184.8, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 11.55, "batchOutput": 92.4, "regionCount": 13, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-1", "name": "GPT-5.1", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5.1", "priceSource": "genai-prices", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5.1", "priceSource": "azure-retail", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": 0.625, "batchOutput": 5, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": 0.625, "batchOutput": 5, "regionCount": 25, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 1.375, "inputMax": 1.71875, "output": 11, "outputMax": 13.75, "cacheRead": 0.1375, "cacheWrite": null, "batchInput": 0.6875, "batchOutput": 5.5, "regionCount": 25, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5", "name": "GPT-5", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5", "priceSource": "genai-prices", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5", "priceSource": "azure-retail", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": 0.625, "batchOutput": 5, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": 0.625, "batchOutput": 5, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 1.375, "inputMax": null, "output": 11, "outputMax": null, "cacheRead": 0.1375, "cacheWrite": null, "batchInput": 0.6875, "batchOutput": 5.5, "regionCount": 13, "regions": [ "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-mini", "name": "GPT-5 mini", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5-mini", "priceSource": "genai-prices", "input": 0.25, "inputMax": null, "output": 2, "outputMax": null, "cacheRead": 0.025, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5-mini", "priceSource": "azure-retail", "input": 0.25, "inputMax": null, "output": 2, "outputMax": null, "cacheRead": 0.025, "cacheWrite": null, "batchInput": 0.125, "batchOutput": 1, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.25, "inputMax": null, "output": 2, "outputMax": null, "cacheRead": 0.025, "cacheWrite": null, "batchInput": 0.125, "batchOutput": 1, "regionCount": 27, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.275, "inputMax": null, "output": 2.2, "outputMax": null, "cacheRead": 0.0275, "cacheWrite": null, "batchInput": 0.1375, "batchOutput": 1.1, "regionCount": 15, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-nano", "name": "GPT-5 nano", "vendor": "OpenAI", "modality": "chat", "context": 272000, "maxOutput": 128000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5-nano", "priceSource": "genai-prices", "input": 0.05, "inputMax": null, "output": 0.4, "outputMax": null, "cacheRead": 0.005, "cacheWrite": null, "batchInput": 0.025, "batchOutput": 0.2, "context": 272000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5-nano", "priceSource": "azure-retail", "input": 0.05, "inputMax": null, "output": 0.4, "outputMax": null, "cacheRead": 0.005, "cacheWrite": null, "batchInput": 0.025, "batchOutput": 0.2, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 11, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.05, "inputMax": null, "output": 0.4, "outputMax": null, "cacheRead": 0.005, "cacheWrite": null, "batchInput": 0.025, "batchOutput": 0.2, "regionCount": 27, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 0.055, "inputMax": null, "output": 0.44, "outputMax": null, "cacheRead": 0.0055, "cacheWrite": null, "batchInput": 0.0275, "batchOutput": 0.22, "regionCount": 15, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-5-pro", "name": "GPT-5 pro", "vendor": "OpenAI", "modality": "chat", "context": 400000, "maxOutput": 272000, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-5-pro", "priceSource": "genai-prices", "input": 15, "inputMax": null, "output": 120, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 7.5, "batchOutput": 60, "context": 400000, "maxOutput": 272000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-5-pro", "priceSource": "azure-retail", "input": 15, "inputMax": null, "output": 120, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 7.5, "batchOutput": 60, "context": 272000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "westeurope", "westus" ], "counts": { "US": 6, "EU": 11, "AP": 5, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 15, "inputMax": null, "output": 120, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 7.5, "batchOutput": 60, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 16.5, "inputMax": null, "output": 132, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 8.25, "batchOutput": 66, "regionCount": 13, "regions": [ "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-4-1", "name": "GPT-4.1", "vendor": "OpenAI", "modality": "chat", "context": 1047576, "maxOutput": 32768, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-4.1", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 1, "batchOutput": 4, "context": 1047576, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-4.1", "priceSource": "azure-retail", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 1, "batchOutput": 4, "context": 1047576, "maxOutput": 32768, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 1, "batchOutput": 4, "regionCount": 28, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 2.2, "inputMax": null, "output": 8.8, "outputMax": null, "cacheRead": 0.55, "cacheWrite": null, "batchInput": 1.1, "batchOutput": 4.4, "regionCount": 16, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "Regional", "input": 2.2, "inputMax": 2.75, "output": 8.8, "outputMax": 11, "cacheRead": 0.55, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 12, "regions": [ "eastus", "eastus2", "northcentralus", "northeurope", "southcentralus", "swedencentral", "switzerlandnorth", "usgovarizona", "usgovvirginia", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-4o", "name": "GPT-4o", "vendor": "OpenAI", "modality": "chat", "context": 128000, "maxOutput": 16384, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-4o", "priceSource": "genai-prices", "input": 2.5, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 1.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 5, "context": 128000, "maxOutput": 16384, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-4o-2024-11-20", "priceSource": "azure-retail", "input": 2.5, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 1.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 5, "context": 128000, "maxOutput": 16384, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 2.5, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 1.25, "cacheWrite": null, "batchInput": 1.25, "batchOutput": 5, "regionCount": 27, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 2.75, "inputMax": 3.438, "output": 11, "outputMax": 13.75, "cacheRead": 1.375, "cacheWrite": null, "batchInput": 1.375, "batchOutput": 5.5, "regionCount": 18, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus3" ] }, { "profile": "Regional", "input": 2.75, "inputMax": 3.438, "output": 11, "outputMax": 13.75, "cacheRead": 1.375, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 21, "regions": [ "australiaeast", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "japaneast", "northcentralus", "northeurope", "norwayeast", "southafricanorth", "southcentralus", "southindia", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-4o-mini", "name": "GPT-4o mini", "vendor": "OpenAI", "modality": "chat", "context": 128000, "maxOutput": 16384, "offers": [ { "endpoint": "openai", "endpointModelId": "gpt-4o-mini", "priceSource": "genai-prices", "input": 0.15, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.075, "batchOutput": 0.3, "context": 128000, "maxOutput": 16384, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "gpt-4o-mini", "priceSource": "azure-retail", "input": 0.15, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.075, "batchOutput": 0.3, "context": 128000, "maxOutput": 16384, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.15, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.075, "batchOutput": 0.3, "regionCount": 28, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.165, "inputMax": 0.207, "output": 0.66, "outputMax": 0.825, "cacheRead": 0.083, "cacheWrite": null, "batchInput": 0.083, "batchOutput": null, "regionCount": 19, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "polandcentral", "southcentralus", "southeastasia", "spaincentral", "swedencentral", "usgovarizona", "usgovvirginia", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "Regional", "input": 0.165, "inputMax": 0.206, "output": 0.66, "outputMax": 0.825, "cacheRead": 0.083, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 12, "regions": [ "eastus", "eastus2", "northcentralus", "northeurope", "southcentralus", "southeastasia", "swedencentral", "usgovarizona", "westcentralus", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "o3", "name": "o3", "vendor": "OpenAI", "modality": "chat", "context": 200000, "maxOutput": 100000, "offers": [ { "endpoint": "openai", "endpointModelId": "o3", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 100000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "o3", "priceSource": "azure-retail", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 1, "batchOutput": 4, "context": 200000, "maxOutput": 100000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 2, "inputMax": null, "output": 8, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": 1, "batchOutput": 4, "regionCount": 24, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 2.2, "inputMax": null, "output": 8.8, "outputMax": null, "cacheRead": 0.55, "cacheWrite": null, "batchInput": 1.1, "batchOutput": 4.4, "regionCount": 13, "regions": [ "eastus", "eastus2", "francecentral", "germanywestcentral", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] }, { "profile": "Regional", "input": 2.2, "inputMax": 2.64, "output": 8.8, "outputMax": 10.56, "cacheRead": 0.55, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 8, "regions": [ "eastus", "eastus2", "northcentralus", "northeurope", "southcentralus", "swedencentral", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "o4-mini", "name": "o4-mini", "vendor": "OpenAI", "modality": "chat", "context": 200000, "maxOutput": 100000, "offers": [ { "endpoint": "openai", "endpointModelId": "o4-mini", "priceSource": "genai-prices", "input": 1.1, "inputMax": null, "output": 4.4, "outputMax": null, "cacheRead": 0.275, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 100000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "o4-mini", "priceSource": "azure-retail", "input": 1.1, "inputMax": null, "output": 4.4, "outputMax": null, "cacheRead": 0.275, "cacheWrite": null, "batchInput": 0.55, "batchOutput": 2.2, "context": 200000, "maxOutput": 100000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 1.1, "inputMax": null, "output": 4.4, "outputMax": null, "cacheRead": 0.275, "cacheWrite": null, "batchInput": 0.55, "batchOutput": 2.2, "regionCount": 26, "regions": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ] }, { "profile": "DataZone", "input": 1.21, "inputMax": 1.32, "output": 4.84, "outputMax": 5.28, "cacheRead": 0.303, "cacheWrite": null, "batchInput": 0.605, "batchOutput": 2.42, "regionCount": 23, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] }, { "profile": "Regional", "input": 1.21, "inputMax": 1.331, "output": 4.84, "outputMax": 5.324, "cacheRead": 0.303, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 7, "regions": [ "eastus", "eastus2", "northcentralus", "southcentralus", "swedencentral", "westus", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "text-embedding-3-large", "name": "text-embedding-3-large", "vendor": "OpenAI", "modality": "embedding", "context": 8191, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "text-embedding-3-large", "priceSource": "genai-prices", "input": 0.13, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 0.065, "batchOutput": 0, "context": 8191, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "text-embedding-3-large", "priceSource": "azure-retail", "input": 0.13, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8191, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 5, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.13, "inputMax": null, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 17, "regions": [ "australiaeast", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "japaneast", "northcentralus", "northeurope", "norwayeast", "southcentralus", "southeastasia", "spaincentral", "swedencentral", "switzerlandnorth", "uksouth", "westeurope" ] }, { "profile": "DataZone", "input": 0.143, "inputMax": 0.156, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] }, { "profile": "Regional", "input": 0.143, "inputMax": 0.172, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 16, "regions": [ "australiaeast", "canadaeast", "eastus", "eastus2", "francecentral", "japaneast", "northcentralus", "northeurope", "norwayeast", "southcentralus", "southeastasia", "swedencentral", "switzerlandnorth", "uksouth", "usgovarizona", "westeurope" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "text-embedding-3-small", "name": "text-embedding-3-small", "vendor": "OpenAI", "modality": "embedding", "context": 8191, "maxOutput": null, "offers": [ { "endpoint": "openai", "endpointModelId": "text-embedding-3-small", "priceSource": "genai-prices", "input": 0.02, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 0.01, "batchOutput": 0, "context": 8191, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://openai.com/api/pricing/", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "text-embedding-3-small", "priceSource": "azure-retail", "input": 0.02, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8191, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "uaenorth", "uksouth", "westeurope", "westus", "westus3" ], "counts": { "US": 7, "EU": 10, "AP": 4, "ME": 2, "other": 2 }, "tiers": null, "scopes": null, "note": "Deployment Regions from the Azure model-availability matrices." }, "azureProfiles": [ { "profile": "Global", "input": 0.02, "inputMax": null, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 17, "regions": [ "australiaeast", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "japaneast", "northcentralus", "northeurope", "norwayeast", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "uksouth", "westeurope", "westus" ] }, { "profile": "DataZone", "input": 0.022, "inputMax": 0.024, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "australiaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanywestcentral", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "westeurope", "westus", "westus3" ] }, { "profile": "Regional", "input": 0.022, "inputMax": 0.027, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 16, "regions": [ "australiaeast", "canadaeast", "eastus", "eastus2", "francecentral", "japaneast", "northcentralus", "northeurope", "norwayeast", "southcentralus", "swedencentral", "switzerlandnorth", "uksouth", "usgovarizona", "westeurope", "westus" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-8-flash", "name": "Gemini 3.8 Flash", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.8-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.8-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-8-flash?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-7-flash", "name": "Gemini 3.7 Flash", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.7-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.7-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-6-flash", "name": "Gemini 3.6 Flash", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.6-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.6-flash", "priceSource": "curated", "input": 0.75, "inputMax": null, "output": 3.75, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": 0.375, "batchOutput": 1.875, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-6-flash?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65535, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.5-flash", "priceSource": "genai-prices", "input": 1.5, "inputMax": null, "output": 9, "outputMax": null, "cacheRead": 0.15, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.5-flash", "priceSource": "genai-prices", "input": 1.5, "inputMax": null, "output": 9, "outputMax": null, "cacheRead": 0.15, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.5-flash-lite", "priceSource": "genai-prices", "input": 0.3, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": 0.03, "cacheWrite": null, "batchInput": 0.15, "batchOutput": 1.25, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.5-flash-lite", "priceSource": "genai-prices", "input": 0.3, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": 0.03, "cacheWrite": null, "batchInput": 0.15, "batchOutput": 1.25, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash-lite?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-1-flash-lite", "name": "Gemini 3.1 Flash-Lite", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.1-flash-lite", "priceSource": "genai-prices", "input": 0.25, "inputMax": null, "output": 1.5, "outputMax": null, "cacheRead": 0.025, "cacheWrite": null, "batchInput": 0.125, "batchOutput": 0.75, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.1-flash-lite", "priceSource": "genai-prices", "input": 0.25, "inputMax": null, "output": 1.5, "outputMax": null, "cacheRead": 0.025, "cacheWrite": null, "batchInput": 0.125, "batchOutput": 0.75, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-1-pro", "name": "Gemini 3.1 Pro", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65536, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3.1-pro-preview", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": 1, "batchOutput": 6, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3.1-pro-preview", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": 1, "batchOutput": 6, "context": 1048576, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "global" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-1-pro?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-3-pro", "name": "Gemini 3 Pro", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65535, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-3-pro-preview", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": 1, "batchOutput": 6, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-3-pro-preview", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 12, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": 1, "batchOutput": 6, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-2-5-pro", "name": "Gemini 2.5 Pro", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65535, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-2.5-pro", "priceSource": "genai-prices", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-2.5-pro", "priceSource": "genai-prices", "input": 1.25, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": 0.125, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "global" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/2-5-pro?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash", "vendor": "Google", "modality": "chat", "context": 1048576, "maxOutput": 65535, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-2.5-flash", "priceSource": "genai-prices", "input": 0.3, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": 0.03, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-2.5-flash", "priceSource": "genai-prices", "input": 0.3, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": 0.03, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": 65535, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "global" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/2-5-flash?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "gemini-embedding-2", "name": "Gemini Embedding 2", "vendor": "Google", "modality": "embedding", "context": 8192, "maxOutput": null, "offers": [ { "endpoint": "gemini", "endpointModelId": "gemini-embedding-2", "priceSource": "curated", "input": 0.2, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8192, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://ai.google.dev/gemini-api/docs/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "gemini-embedding-2", "priceSource": "curated", "input": 0.2, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8192, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "global" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/gemini/embedding-2?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "grok-4-7", "name": "Grok 4.7", "vendor": "xAI", "modality": "chat", "context": 500000, "maxOutput": null, "offers": [ { "endpoint": "xai", "endpointModelId": "grok-4.7", "priceSource": "curated", "input": 2, "inputMax": null, "output": 6, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://x.ai/api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "xai.grok-4.7", "priceSource": "aws-price-list", "input": 2.2, "inputMax": null, "output": 6.6, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": null, "regions": { "known": true, "available": [ "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-7", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 12, "ME": 2, "other": 2 }, "tiers": { "inRegion": [], "geo": [ "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-7", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 33, "uniformAcrossRegions": true } } ] }, { "slug": "grok-4-6", "name": "Grok 4.6", "vendor": "xAI", "modality": "chat", "context": 500000, "maxOutput": null, "offers": [ { "endpoint": "xai", "endpointModelId": "grok-4.6", "priceSource": "curated", "input": 2, "inputMax": null, "output": 6, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://x.ai/api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "xai.grok-4.6", "priceSource": "aws-price-list", "input": 2.2, "inputMax": null, "output": 6.6, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": null, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 6, "EU": 8, "AP": 13, "ME": 4, "other": 3 }, "tiers": { "inRegion": [ "us-gov-east-1" ], "geo": [ "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-6.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 34, "uniformAcrossRegions": true } }, { "endpoint": "vertex", "endpointModelId": "xai/grok-4.6", "priceSource": "curated", "input": 2, "inputMax": null, "output": 6, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "grok-4-5", "name": "Grok 4.5", "vendor": "xAI", "modality": "chat", "context": 500000, "maxOutput": 500000, "offers": [ { "endpoint": "xai", "endpointModelId": "grok-4.5", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 6, "outputMax": null, "cacheRead": 0.5, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 500000, "maxOutput": 500000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://x.ai/api", "priceAsOf": "2026-10-01" } ] }, { "slug": "grok-4-3", "name": "Grok 4.3", "vendor": "xAI", "modality": "chat", "context": 1000000, "maxOutput": 1000000, "offers": [ { "endpoint": "xai", "endpointModelId": "grok-4.3", "priceSource": "genai-prices", "input": 1.25, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": 0.2, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 1000000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://x.ai/api", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "xai.grok-4.3", "priceSource": "aws-price-list", "input": 1.25, "inputMax": 1.5, "output": 2.5, "outputMax": 3, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "counts": { "US": 4 }, "tiers": { "inRegion": [ "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "geo": [ "us-east-1", "us-east-2", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-3.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 4, "uniformAcrossRegions": false } } ] }, { "slug": "grok-4-1-fast", "name": "Grok 4.1 Fast (reasoning)", "vendor": "xAI", "modality": "chat", "context": 2000000, "maxOutput": 2000000, "offers": [ { "endpoint": "xai", "endpointModelId": "grok-4-1-fast-reasoning", "priceSource": "genai-prices", "input": 0.2, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": 0.05, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 2000000, "maxOutput": 2000000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://x.ai/api", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "grok-4-1-fast-reasoning", "priceSource": "azure-retail", "input": 0.2, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 131072, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 13, "AP": 11, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.2, "inputMax": 0.25, "output": 0.5, "outputMax": 0.63, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 41, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.22, "inputMax": null, "output": 0.55, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "xai/grok-4.1-fast-reasoning", "priceSource": "curated", "input": 0.2, "inputMax": null, "output": 0.5, "outputMax": null, "cacheRead": 0.05, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 2000000, "maxOutput": 2000000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": [ "eu", "global", "us" ], "note": "Vertex documents endpoint scopes rather than a machine-readable Region matrix." }, "azureProfiles": null, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models?hl=en", "priceAsOf": "2026-10-01" } ] }, { "slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "vendor": "DeepSeek", "modality": "chat", "context": 1000000, "maxOutput": 8192, "offers": [ { "endpoint": "deepseek", "endpointModelId": "deepseek-v4-pro", "priceSource": "genai-prices", "input": 0.435, "inputMax": null, "output": 0.87, "outputMax": null, "cacheRead": 0.003625, "cacheWrite": 0, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 8192, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://api-docs.deepseek.com/quick_start/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "deepseek-v4-pro", "priceSource": "azure-retail", "input": 1.74, "inputMax": null, "output": 3.48, "outputMax": null, "cacheRead": 0.145, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 384000, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 15, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 1.74, "inputMax": 2.09, "output": 3.48, "outputMax": 4.18, "cacheRead": 0.145, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 1.91, "inputMax": 2.3, "output": 3.83, "outputMax": 4.59, "cacheRead": 0.16, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 25, "regions": [ "belgiumcentral", "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "deepseek-flash", "name": "DeepSeek Flash", "vendor": "DeepSeek", "modality": "chat", "context": 1000000, "maxOutput": 384000, "offers": [ { "endpoint": "deepseek", "endpointModelId": "deepseek-flash", "priceSource": "curated", "input": 0.3, "inputMax": null, "output": 1.2, "outputMax": null, "cacheRead": 0.006, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 384000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://api-docs.deepseek.com/quick_start/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "deepseek-v4-flash", "priceSource": "azure-retail", "input": 0.19, "inputMax": null, "output": 0.51, "outputMax": null, "cacheRead": 0.028, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 384000, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 15, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.19, "inputMax": 0.23, "output": 0.51, "outputMax": 0.61, "cacheRead": 0.028, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.21, "inputMax": 0.25, "output": 0.56, "outputMax": 0.67, "cacheRead": 0.031, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 25, "regions": [ "belgiumcentral", "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "deepseek-v3-2", "name": "DeepSeek V3.2", "vendor": "DeepSeek", "modality": "chat", "context": 163840, "maxOutput": 163840, "offers": [ { "endpoint": "deepseek", "endpointModelId": "deepseek-v3.2", "priceSource": "genai-prices", "input": 0.2288, "inputMax": null, "output": 0.3432, "outputMax": null, "cacheRead": 0.028, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 163840, "maxOutput": 163840, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://api-docs.deepseek.com/quick_start/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "us.deepseek.v3.2", "priceSource": "aws-price-list", "input": 0.62, "inputMax": 0.961, "output": 1.85, "outputMax": 2.8675, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 163840, "maxOutput": 163840, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 2, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-2.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "azure", "endpointModelId": "deepseek-v3.2", "priceSource": "azure-retail", "input": 0.58, "inputMax": null, "output": 1.68, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 163840, "maxOutput": 163840, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 15, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.58, "inputMax": 0.73, "output": 1.68, "outputMax": 2.1, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.64, "inputMax": 0.8, "output": 1.85, "outputMax": 2.3, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 41, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "deepseek-ai/deepseek-v3.2-maas", "priceSource": "curated", "input": 0.56, "inputMax": null, "output": 1.68, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 0.28, "batchOutput": 0.84, "context": 163840, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "mistral-large-3", "name": "Mistral Large 3", "vendor": "Mistral", "modality": "chat", "context": 262144, "maxOutput": 262144, "offers": [ { "endpoint": "mistral", "endpointModelId": "mistral-large-3", "priceSource": "curated", "input": 0.5, "inputMax": null, "output": 1.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "mistral.mistral-large-3-675b-instruct", "priceSource": "aws-price-list", "input": 0.5, "inputMax": 0.775, "output": 1.5, "outputMax": 2.325, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "AP": 3, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-mistral-large-3.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "azure", "endpointModelId": "mistral-large-3", "priceSource": "azure-retail", "input": 0.5, "inputMax": null, "output": 1.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": 8191, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 11, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.5, "inputMax": 0.63, "output": 1.5, "outputMax": 1.88, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.55, "inputMax": null, "output": 1.65, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "belgiumcentral", "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "mistral-medium-3-5", "name": "Mistral Medium 3.5", "vendor": "Mistral", "modality": "chat", "context": 262144, "maxOutput": 262144, "offers": [ { "endpoint": "mistral", "endpointModelId": "mistral-medium-3-5", "priceSource": "curated", "input": 1.5, "inputMax": null, "output": 7.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "magistral-medium", "name": "Magistral Medium 1.2", "vendor": "Mistral", "modality": "chat", "context": 40000, "maxOutput": 40000, "offers": [ { "endpoint": "mistral", "endpointModelId": "magistral-medium-1-2-2509", "priceSource": "genai-prices", "input": 2, "inputMax": null, "output": 5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 40000, "maxOutput": 40000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "ministral-3-8b", "name": "Ministral 3 8B", "vendor": "Mistral", "modality": "chat", "context": 262144, "maxOutput": 262144, "offers": [ { "endpoint": "mistral", "endpointModelId": "ministral-3-8b-2512", "priceSource": "curated", "input": 0.15, "inputMax": null, "output": 0.15, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "mistral.ministral-3-8b-instruct", "priceSource": "aws-price-list", "input": 0.15, "inputMax": 0.23, "output": 0.15, "outputMax": 0.23, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 3, "AP": 3, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-3-8b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "ministral-3-14b", "name": "Ministral 3 14B", "vendor": "Mistral", "modality": "chat", "context": 128000, "maxOutput": 8192, "offers": [ { "endpoint": "mistral", "endpointModelId": "ministral-14b-2512", "priceSource": "genai-prices", "input": 0.2, "inputMax": null, "output": 0.2, "outputMax": null, "cacheRead": 0.02, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "mistral.ministral-3-14b-instruct", "priceSource": "aws-price-list", "input": 0.2, "inputMax": 0.31, "output": 0.2, "outputMax": 0.31, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 3, "AP": 3, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-14b-3-0.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "ministral-3-3b", "name": "Ministral 3 3B", "vendor": "Mistral", "modality": "chat", "context": 128000, "maxOutput": 8192, "offers": [ { "endpoint": "mistral", "endpointModelId": "ministral-3b-2512", "priceSource": "genai-prices", "input": 0.1, "inputMax": null, "output": 0.1, "outputMax": null, "cacheRead": 0.01, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": null, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "mistral.ministral-3-3b-instruct", "priceSource": "aws-price-list", "input": 0.1, "inputMax": 0.16, "output": 0.1, "outputMax": 0.16, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 3, "AP": 3, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-mistral-ai-ministral-3b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "codestral", "name": "Codestral 2508", "vendor": "Mistral", "modality": "chat", "context": 256000, "maxOutput": 256000, "offers": [ { "endpoint": "mistral", "endpointModelId": "codestral-2508", "priceSource": "genai-prices", "input": 0.3, "inputMax": null, "output": 0.9, "outputMax": null, "cacheRead": 0.03, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": 256000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "mistral-embed", "name": "Mistral Embed", "vendor": "Mistral", "modality": "embedding", "context": 8192, "maxOutput": null, "offers": [ { "endpoint": "mistral", "endpointModelId": "mistral-embed", "priceSource": "genai-prices", "input": 0.1, "inputMax": null, "output": 0.1, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8192, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://mistral.ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "llama-4-maverick", "name": "Llama 4 Maverick 17B", "vendor": "Meta", "modality": "chat", "context": 128000, "maxOutput": 4096, "offers": [ { "endpoint": "bedrock", "endpointModelId": "meta.llama4-maverick-17b-instruct-v1:0", "priceSource": "aws-price-list", "input": 0.24, "inputMax": null, "output": 0.97, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 0.12, "batchOutput": 0.485, "context": 128000, "maxOutput": 4096, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4 }, "tiers": { "inRegion": [], "geo": [ "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-maverick-17b-instruct.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 4, "uniformAcrossRegions": true } }, { "endpoint": "azure", "endpointModelId": "Llama-4-Maverick-17B-128E-Instruct-FP8", "priceSource": "azure-retail", "input": 0.25, "inputMax": null, "output": 1, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 16384, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 11, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.25, "inputMax": 0.313, "output": 1, "outputMax": 1.25, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.275, "inputMax": null, "output": 1.1, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "belgiumcentral", "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "Regional", "input": 0.275, "inputMax": 0.33, "output": 1.1, "outputMax": 1.32, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 17, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "spaincentral", "swedencentral", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "groq", "endpointModelId": "meta-llama/llama-4-maverick-17b-128e-instruct", "priceSource": "genai-prices", "input": 0.2, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 8192, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "meta/llama-4-maverick-17b-128e-instruct-maas", "priceSource": "curated", "input": 0.35, "inputMax": null, "output": 1.15, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 1000000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "llama-4-scout", "name": "Llama 4 Scout 17B", "vendor": "Meta", "modality": "chat", "context": 128000, "maxOutput": 4096, "offers": [ { "endpoint": "bedrock", "endpointModelId": "meta.llama4-scout-17b-instruct-v1:0", "priceSource": "aws-price-list", "input": 0.17, "inputMax": null, "output": 0.66, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": 0.085, "batchOutput": 0.33, "context": 128000, "maxOutput": 4096, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4 }, "tiers": { "inRegion": [], "geo": [ "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-4-scout-17b-instruct.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 4, "uniformAcrossRegions": true } }, { "endpoint": "azure", "endpointModelId": "Llama-4-Scout-17B-16E-Instruct", "priceSource": "curated", "input": 0.2, "inputMax": null, "output": 0.78, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 10000000, "maxOutput": 16384, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Azure Region availability not published for this model." }, "azureProfiles": null, "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "groq", "endpointModelId": "meta-llama/llama-4-scout-17b-16e-instruct", "priceSource": "genai-prices", "input": 0.11, "inputMax": null, "output": 0.34, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 8192, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "meta/llama-4-scout-17b-16e-instruct-maas", "priceSource": "curated", "input": 0.25, "inputMax": null, "output": 0.7, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 10000000, "maxOutput": 10000000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "llama-3-3-70b", "name": "Llama 3.3 70B", "vendor": "Meta", "modality": "chat", "context": 128000, "maxOutput": 4096, "offers": [ { "endpoint": "bedrock", "endpointModelId": "meta.llama3-3-70b-instruct-v1:0", "priceSource": "aws-price-list", "input": 0.72, "inputMax": null, "output": 0.72, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 4096, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3 }, "tiers": { "inRegion": [ "us-east-2" ], "geo": [ "us-east-1", "us-east-2", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-meta-llama-3-3-70b-instruct.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 3, "uniformAcrossRegions": true } }, { "endpoint": "azure", "endpointModelId": "Llama-3.3-70B-Instruct", "priceSource": "azure-retail", "input": 0.71, "inputMax": null, "output": 0.71, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 2048, "regions": { "known": true, "available": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 11, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.71, "inputMax": 0.888, "output": 0.71, "outputMax": 0.888, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 42, "regions": [ "australiaeast", "belgiumcentral", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastasia", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "jioindiawest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.781, "inputMax": null, "output": 0.781, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "belgiumcentral", "centralus", "eastus", "eastus2", "francecentral", "germanynorth", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "Regional", "input": 0.781, "inputMax": 0.937, "output": 0.781, "outputMax": 0.937, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 17, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "polandcentral", "southcentralus", "southeastasia", "spaincentral", "swedencentral", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "groq", "endpointModelId": "llama-3.3-70b-versatile", "priceSource": "genai-prices", "input": 0.59, "inputMax": null, "output": 0.79, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "nova-2-pro", "name": "Nova 2 Pro", "vendor": "Amazon", "modality": "chat", "context": 1000000, "maxOutput": 64000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "us.amazon.nova-2-pro-preview-20251202-v1:0", "priceSource": "aws-price-list", "input": 1.375, "inputMax": 1.771, "output": 11, "outputMax": 14.124, "cacheRead": 0.546875, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://aws.amazon.com/bedrock/pricing/", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 6, "uniformAcrossRegions": false } } ] }, { "slug": "nova-2-lite", "name": "Nova 2 Lite", "vendor": "Amazon", "modality": "chat", "context": 1000000, "maxOutput": 64000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "us.amazon.nova-2-lite-v1:0", "priceSource": "aws-price-list", "input": 0.3, "inputMax": 0.528, "output": 2.5, "outputMax": 4.411, "cacheRead": 0.0825, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 64000, "regions": { "known": true, "available": [ "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 7, "AP": 11, "ME": 2, "other": 2 }, "tiers": { "inRegion": [], "geo": [ "ap-northeast-1", "ca-central-1", "ca-west-1", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-2-lite.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "nova-premier", "name": "Nova Premier", "vendor": "Amazon", "modality": "chat", "context": 1000000, "maxOutput": 25000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "amazon.nova-premier-v1:0", "priceSource": "aws-price-list", "input": 2.5, "inputMax": null, "output": 12.5, "outputMax": null, "cacheRead": 0.625, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 25000, "regions": { "known": true, "available": [ "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3 }, "tiers": { "inRegion": [], "geo": [ "us-east-1", "us-east-2", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-premier.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 3, "uniformAcrossRegions": true } } ] }, { "slug": "nova-pro", "name": "Nova Pro", "vendor": "Amazon", "modality": "chat", "context": 300000, "maxOutput": 10000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "amazon.nova-pro-v1:0", "priceSource": "aws-price-list", "input": 0.8, "inputMax": 1.28, "output": 3.2, "outputMax": 5.21, "cacheRead": 0.2, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 300000, "maxOutput": 10000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 5, "EU": 7, "AP": 6, "ME": 2 }, "tiers": { "inRegion": [ "ap-southeast-2", "ap-southeast-3", "eu-west-2", "me-central-1", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-3", "il-central-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-pro.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 20, "uniformAcrossRegions": false } } ] }, { "slug": "nova-lite", "name": "Nova Lite", "vendor": "Amazon", "modality": "chat", "context": 300000, "maxOutput": 10000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "amazon.nova-lite-v1:0", "priceSource": "aws-price-list", "input": 0.06, "inputMax": 0.096, "output": 0.24, "outputMax": 0.384, "cacheRead": 0.015, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 300000, "maxOutput": 10000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ca-central-1", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-1", "us-west-2" ], "counts": { "US": 5, "EU": 7, "AP": 6, "ME": 2, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "me-central-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "geo": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "ca-central-1", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-3", "il-central-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-lite.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 23, "uniformAcrossRegions": false } } ] }, { "slug": "nova-micro", "name": "Nova Micro", "vendor": "Amazon", "modality": "chat", "context": 128000, "maxOutput": 10000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "amazon.nova-micro-v1:0", "priceSource": "aws-price-list", "input": 0.035, "inputMax": 0.056, "output": 0.14, "outputMax": 0.224, "cacheRead": 0.00875, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 10000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 7, "AP": 5, "ME": 1 }, "tiers": { "inRegion": [ "ap-southeast-2", "eu-west-2", "us-east-1", "us-gov-west-1" ], "geo": [ "ap-northeast-1", "ap-northeast-2", "ap-south-1", "ap-southeast-1", "ap-southeast-2", "eu-central-1", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-3", "il-central-1", "us-east-1", "us-east-2", "us-west-2" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-nova-micro.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 18, "uniformAcrossRegions": false } } ] }, { "slug": "titan-embed-text-v2", "name": "Titan Text Embeddings V2", "vendor": "Amazon", "modality": "embedding", "context": 8192, "maxOutput": null, "offers": [ { "endpoint": "bedrock", "endpointModelId": "amazon.titan-embed-text-v2:0", "priceSource": "curated", "input": 0.02, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 8192, "maxOutput": null, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-2", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "counts": { "US": 5, "EU": 8, "AP": 6, "other": 2 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-2", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-titan-text-embeddings-v2.html", "priceAsOf": "2026-10-01" } ] }, { "slug": "qwen3-coder-480b", "name": "Qwen3 Coder 480B A35B", "vendor": "Alibaba", "modality": "chat", "context": 262000, "maxOutput": 65536, "offers": [ { "endpoint": "bedrock", "endpointModelId": "qwen.qwen3-coder-480b-a35b-v1:0", "priceSource": "aws-price-list", "input": 0.45, "inputMax": 0.7, "output": 1.8, "outputMax": 2.79, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262000, "maxOutput": 65536, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "us-east-2", "us-west-2" ], "counts": { "US": 2, "EU": 2, "AP": 4 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "vertex", "endpointModelId": "qwen/qwen3-coder-480b-a35b-instruct-maas", "priceSource": "curated", "input": 0.22, "inputMax": null, "output": 1.8, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "qwen3-coder-next", "name": "Qwen3 Coder Next", "vendor": "Alibaba", "modality": "chat", "context": 256000, "maxOutput": 16384, "offers": [ { "endpoint": "bedrock", "endpointModelId": "qwen.qwen3-coder-next", "priceSource": "aws-price-list", "input": 0.5, "inputMax": 0.78, "output": 1.2, "outputMax": 1.86, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": 16384, "regions": { "known": true, "available": [ "ap-southeast-2", "eu-west-2", "us-east-1" ], "counts": { "US": 1, "EU": 1, "AP": 1 }, "tiers": { "inRegion": [ "ap-southeast-2", "eu-west-2", "us-east-1" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-next.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "qwen3-235b-a22b", "name": "Qwen3 235B A22B 2507", "vendor": "Alibaba", "modality": "chat", "context": 262144, "maxOutput": 131072, "offers": [ { "endpoint": "bedrock", "endpointModelId": "qwen.qwen3-235b-a22b-2507-v1:0", "priceSource": "aws-price-list", "input": 0.22, "inputMax": 0.34, "output": 0.88, "outputMax": 1.37, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 131072, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-2", "us-east-2", "us-west-2" ], "counts": { "US": 2, "EU": 4, "AP": 4 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-2", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "vertex", "endpointModelId": "qwen/qwen3-235b-a22b-instruct-2507-maas", "priceSource": "curated", "input": 0.25, "inputMax": null, "output": 1, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 16384, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "qwen3-next-80b", "name": "Qwen3 Next 80B A3B", "vendor": "Alibaba", "modality": "chat", "context": 256000, "maxOutput": 8192, "offers": [ { "endpoint": "bedrock", "endpointModelId": "qwen.qwen3-next-80b-a3b", "priceSource": "aws-price-list", "input": 0.14, "inputMax": 0.217, "output": 1.2, "outputMax": 1.86, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 3, "AP": 3, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "qwen3-32b", "name": "Qwen3 32B", "vendor": "Alibaba", "modality": "chat", "context": 131072, "maxOutput": 16384, "offers": [ { "endpoint": "bedrock", "endpointModelId": "qwen.qwen3-32b-v1:0", "priceSource": "aws-price-list", "input": 0.15, "inputMax": 0.23, "output": 0.6, "outputMax": 0.93, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 16384, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 5, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "groq", "endpointModelId": "qwen/qwen3-32b", "priceSource": "genai-prices", "input": 0.29, "inputMax": null, "output": 0.59, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131000, "maxOutput": 131000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-oss-120b", "name": "gpt-oss-120b", "vendor": "OpenAI", "modality": "chat", "context": 128000, "maxOutput": 128000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "openai.gpt-oss-120b-1:0", "priceSource": "aws-price-list", "input": 0.15, "inputMax": 0.23, "output": 0.6, "outputMax": 0.93, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 128000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "counts": { "US": 5, "EU": 5, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "geo": [ "us-gov-east-1", "us-gov-west-1" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-120b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "azure", "endpointModelId": "gpt-oss-120b", "priceSource": "azure-retail", "input": 0.15, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 131072, "regions": { "known": true, "available": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.15, "inputMax": 0.19, "output": 0.6, "outputMax": 0.75, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 40, "regions": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.165, "inputMax": null, "output": 0.66, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 20, "regions": [ "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "groq", "endpointModelId": "openai/gpt-oss-120b", "priceSource": "genai-prices", "input": 0.15, "inputMax": null, "output": 0.6, "outputMax": null, "cacheRead": 0.075, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "openai/gpt-oss-120b-maas", "priceSource": "curated", "input": 0.09, "inputMax": null, "output": 0.36, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "gpt-oss-20b", "name": "gpt-oss-20b", "vendor": "OpenAI", "modality": "chat", "context": 128000, "maxOutput": 128000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "openai.gpt-oss-20b-1:0", "priceSource": "aws-price-list", "input": 0.07, "inputMax": 0.11, "output": 0.3, "outputMax": 0.47, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 128000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-gov-east-1", "us-gov-west-1", "us-west-2" ], "counts": { "US": 5, "EU": 5, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-gov-west-1", "us-west-2" ], "geo": [ "us-gov-east-1", "us-gov-west-1" ], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-oss-20b.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "groq", "endpointModelId": "openai/gpt-oss-20b", "priceSource": "genai-prices", "input": 0.075, "inputMax": null, "output": 0.3, "outputMax": null, "cacheRead": 0.0375, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 65536, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://groq.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "openai/gpt-oss-20b-maas", "priceSource": "curated", "input": 0.07, "inputMax": null, "output": 0.25, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 131072, "maxOutput": 32768, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "kimi-k3", "name": "Kimi K3", "vendor": "Moonshot AI", "modality": "chat", "context": 1048576, "maxOutput": null, "offers": [ { "endpoint": "bedrock", "endpointModelId": "moonshotai.kimi-k3", "priceSource": "aws-price-list", "input": 3.3, "inputMax": null, "output": 16.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": null, "regions": { "known": true, "available": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 13, "ME": 4, "other": 3 }, "tiers": { "inRegion": [], "geo": [ "ca-central-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "af-south-1", "ap-east-2", "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ap-southeast-5", "ap-southeast-6", "ap-southeast-7", "ca-central-1", "ca-west-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "il-central-1", "me-central-1", "me-south-1", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k3.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 34, "uniformAcrossRegions": true } }, { "endpoint": "azure", "endpointModelId": "kimi-k3", "priceSource": "azure-retail", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1048576, "maxOutput": null, "regions": { "known": true, "available": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 8, "EU": 12 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 3, "inputMax": null, "output": 15, "outputMax": null, "cacheRead": 0.3, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 20, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 3.3, "inputMax": null, "output": 16.5, "outputMax": null, "cacheRead": 0.33, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 20, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "kimi-k2-5", "name": "Kimi K2.5", "vendor": "Moonshot AI", "modality": "chat", "context": 262144, "maxOutput": 262144, "offers": [ { "endpoint": "bedrock", "endpointModelId": "moonshotai.kimi-k2.5", "priceSource": "aws-price-list", "input": 0.6, "inputMax": 0.93, "output": 3, "outputMax": 4.65, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 2, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-5.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "azure", "endpointModelId": "kimi-k2.5", "priceSource": "azure-retail", "input": 0.6, "inputMax": null, "output": 3, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 13, "AP": 7, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.6, "inputMax": 0.75, "output": 3, "outputMax": 3.75, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 37, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.66, "inputMax": 0.825, "output": 3.3, "outputMax": 4.125, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 21, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "kimi-k2-thinking", "name": "Kimi K2 Thinking", "vendor": "Moonshot AI", "modality": "chat", "context": 128000, "maxOutput": 8192, "offers": [ { "endpoint": "bedrock", "endpointModelId": "moonshot.kimi-k2-thinking", "priceSource": "aws-price-list", "input": 0.6, "inputMax": 0.93, "output": 2.5, "outputMax": 3.875, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": 8192, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://aws.amazon.com/bedrock/pricing/", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "azure", "endpointModelId": "kimi-k2.6", "priceSource": "azure-retail", "input": 0.6, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 262144, "maxOutput": 262144, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 12, "AP": 6, "ME": 2, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.6, "inputMax": 0.75, "output": 2.5, "outputMax": 3.13, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 34, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.66, "inputMax": 0.83, "output": 2.75, "outputMax": 3.44, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 34, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "japaneast", "japanwest", "koreacentral", "northcentralus", "norwayeast", "polandcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" }, { "endpoint": "vertex", "endpointModelId": "moonshotai/kimi-k2-thinking-maas", "priceSource": "curated", "input": 0.6, "inputMax": null, "output": 2.5, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": 256000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "command-a", "name": "Cohere Command A", "vendor": "Cohere", "modality": "chat", "context": 256000, "maxOutput": null, "offers": [ { "endpoint": "cohere", "endpointModelId": "command-a", "priceSource": "genai-prices", "input": 2.5, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://cohere.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "command-a", "priceSource": "azure-retail", "input": 2.5, "inputMax": null, "output": 10, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 256000, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 2.5, "inputMax": 3.125, "output": 10, "outputMax": 12.5, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 41, "regions": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 2.75, "inputMax": 3.4, "output": 11, "outputMax": 13.75, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "cohere-embed-v4", "name": "Cohere Embed v4", "vendor": "Cohere", "modality": "embedding", "context": 128000, "maxOutput": null, "offers": [ { "endpoint": "cohere", "endpointModelId": "embed-v4.0", "priceSource": "genai-prices", "input": 0.12, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": null, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Direct API — one global endpoint, no per-Region deployment." }, "azureProfiles": null, "source": "https://cohere.com/pricing", "priceAsOf": "2026-10-01" }, { "endpoint": "bedrock", "endpointModelId": "cohere.embed-v4:0", "priceSource": "curated", "input": 0.12, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": null, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "counts": { "US": 4, "EU": 8, "AP": 9, "other": 2 }, "tiers": { "inRegion": [ "ap-northeast-1", "eu-west-1", "us-east-1" ], "geo": [ "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ], "global": [ "ap-northeast-1", "ap-northeast-2", "ap-northeast-3", "ap-south-1", "ap-south-2", "ap-southeast-1", "ap-southeast-2", "ap-southeast-3", "ap-southeast-4", "ca-central-1", "eu-central-1", "eu-central-2", "eu-north-1", "eu-south-1", "eu-south-2", "eu-west-1", "eu-west-2", "eu-west-3", "sa-east-1", "us-east-1", "us-east-2", "us-west-1", "us-west-2" ] }, "scopes": null, "note": "On-demand price is set per model, not per Region — this column is about availability and routing." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-cohere-embed-v4.html", "priceAsOf": "2026-10-01" }, { "endpoint": "azure", "endpointModelId": "embed-v-4-0", "priceSource": "azure-retail", "input": 0.12, "inputMax": null, "output": 0, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 128000, "maxOutput": null, "regions": { "known": true, "available": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 11, "EU": 14, "AP": 10, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "Global", "input": 0.12, "inputMax": 0.15, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 41, "regions": [ "australiaeast", "australiasoutheast", "brazilsouth", "canadacentral", "canadaeast", "centralindia", "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "DataZone", "input": 0.132, "inputMax": 0.165, "output": null, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 23, "regions": [ "centralus", "denmarkeast", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "usgovarizona", "usgovvirginia", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "glm-5-3", "name": "GLM 5.3", "vendor": "Z.ai", "modality": "chat", "context": 1000000, "maxOutput": 128000, "offers": [ { "endpoint": "azure", "endpointModelId": "glm-5.3", "priceSource": "azure-retail", "input": 2.1, "inputMax": null, "output": 6.6, "outputMax": null, "cacheRead": 0.39, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 128000, "regions": { "known": true, "available": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 9, "EU": 13, "AP": 8, "ME": 3, "other": 3 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "DataZone", "input": 2.1, "inputMax": null, "output": 6.6, "outputMax": null, "cacheRead": 0.39, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 23, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] }, { "profile": "Regional", "input": 1.75, "inputMax": null, "output": 5.5, "outputMax": null, "cacheRead": 0.325, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 36, "regions": [ "australiaeast", "brazilsouth", "canadacentral", "canadaeast", "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "indonesiacentral", "italynorth", "japaneast", "japanwest", "koreacentral", "malaysiawest", "northcentralus", "northeurope", "norwayeast", "polandcentral", "qatarcentral", "southafricanorth", "southcentralus", "southeastasia", "southindia", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uaenorth", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "glm-5", "name": "GLM 5", "vendor": "Z.ai", "modality": "chat", "context": 200000, "maxOutput": 128000, "offers": [ { "endpoint": "bedrock", "endpointModelId": "zai.glm-5", "priceSource": "aws-price-list", "input": 1, "inputMax": 1.55, "output": 3.2, "outputMax": 4.96, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 128000, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 2, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-5.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } }, { "endpoint": "vertex", "endpointModelId": "zai-org/glm-5-maas", "priceSource": "curated", "input": 1, "inputMax": null, "output": 3.2, "outputMax": null, "cacheRead": 0.1, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 200000, "maxOutput": 128000, "regions": { "known": false, "available": null, "counts": null, "tiers": null, "scopes": null, "note": "Vertex publishes availability in a client-rendered table — not machine-readable." }, "azureProfiles": null, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "priceAsOf": "2026-10-01" } ] }, { "slug": "glm-4-7", "name": "GLM 4.7", "vendor": "Z.ai", "modality": "chat", "context": 203000, "maxOutput": 4096, "offers": [ { "endpoint": "bedrock", "endpointModelId": "zai.glm-4.7", "priceSource": "aws-price-list", "input": 0.6, "inputMax": 0.93, "output": 2.2, "outputMax": 3.41, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 203000, "maxOutput": 4096, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 2, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-north-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-4-7.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] }, { "slug": "minimax-m3", "name": "MiniMax M3", "vendor": "MiniMax", "modality": "chat", "context": 1000000, "maxOutput": null, "offers": [ { "endpoint": "azure", "endpointModelId": "minimax-m3", "priceSource": "azure-retail", "input": 0.33, "inputMax": null, "output": 1.32, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": null, "regions": { "known": true, "available": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ], "counts": { "US": 9, "EU": 13 }, "tiers": null, "scopes": null, "note": "Regions inferred from the Regions the model has retail meters in." }, "azureProfiles": [ { "profile": "DataZone", "input": 0.33, "inputMax": null, "output": 1.32, "outputMax": null, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "regionCount": 22, "regions": [ "centralus", "eastus", "eastus2", "francecentral", "germanywestcentral", "italynorth", "northcentralus", "northeurope", "norwayeast", "polandcentral", "southcentralus", "spaincentral", "swedencentral", "switzerlandnorth", "switzerlandwest", "uksouth", "ukwest", "westcentralus", "westeurope", "westus", "westus2", "westus3" ] } ], "source": "https://azure.microsoft.com/pricing/details/phi-3/", "priceAsOf": "2026-10-01" } ] }, { "slug": "minimax-m2-5", "name": "MiniMax M2.5", "vendor": "MiniMax", "modality": "chat", "context": 1000000, "maxOutput": 8192, "offers": [ { "endpoint": "bedrock", "endpointModelId": "minimax.minimax-m2.5", "priceSource": "aws-price-list", "input": 0.3, "inputMax": 0.47, "output": 1.2, "outputMax": 1.86, "cacheRead": null, "cacheWrite": null, "batchInput": null, "batchOutput": null, "context": 1000000, "maxOutput": 8192, "regions": { "known": true, "available": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "counts": { "US": 3, "EU": 5, "AP": 4, "other": 1 }, "tiers": { "inRegion": [ "ap-northeast-1", "ap-south-1", "ap-southeast-2", "ap-southeast-3", "eu-central-1", "eu-north-1", "eu-south-1", "eu-west-1", "eu-west-2", "sa-east-1", "us-east-1", "us-east-2", "us-west-2" ], "geo": [], "global": [] }, "scopes": null, "note": "On-demand price varies by Region for this model — the range below is across all priced Regions." }, "azureProfiles": null, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-minimax-minimax-m2-5.html", "priceAsOf": "2026-10-01", "awsPriceList": { "regionCount": 13, "uniformAcrossRegions": false } } ] } ], "sources": [ { "id": "aws-bedrock-prices", "label": "AWS Price List (Amazon Bedrock)", "url": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json", "ok": true }, { "id": "aws-bedrock-regions", "label": "AWS Bedrock Regional availability", "url": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html", "ok": true }, { "id": "azure-model-matrix-0", "label": "Azure model availability matrix", "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/foundry/openai/includes/model-matrix/standard-global.md", "ok": true }, { "id": "azure-model-matrix-1", "label": "Azure model availability matrix", "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/foundry/openai/includes/model-matrix/datazone-standard.md", "ok": true }, { "id": "azure-model-matrix-2", "label": "Azure model availability matrix", "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/foundry/openai/includes/model-matrix/standard-models.md", "ok": true }, { "id": "azure-model-matrix-3", "label": "Azure model availability matrix", "url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-ai-docs/main/articles/foundry/openai/includes/model-matrix/global-batch.md", "ok": true }, { "id": "azure-retail-prices", "label": "Azure Retail Prices API (Foundry Models)", "url": "https://prices.azure.com/api/retail/prices?api-version=2023-01-01-preview&$filter=serviceName%20eq%20'Foundry%20Models'", "ok": true }, { "id": "genai-prices", "label": "pydantic/genai-prices (price backbone)", "url": "https://raw.githubusercontent.com/pydantic/genai-prices/main/prices/data.json", "ok": true }, { "id": "vertex-locations", "label": "Vertex AI locations", "url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations?hl=en", "ok": true } ], "dataQuality": { "notes": [ "Bedrock on-demand token prices are set per model, not per Region — the Region story on Bedrock is availability and routing tier, not price.", "GovCloud and the isolated Regions are priced separately from the commercial AWS list, so their meters are excluded from every Bedrock price on this page. A model AWS has not yet listed commercially shows no Bedrock price at all rather than a GovCloud rate — those rows are in dataQuality.gaps under gov-cloud-only-price. Region availability is read from the Bedrock docs and is unaffected.", "Azure prices do move: Data Zone Standard is billed differently in the EU/US zone than in the Asia Pacific zone, and some Regions carry an uplift on Global Standard too. Where a profile has more than one price we show the range.", "Anthropic models sold through AWS Marketplace are absent from the AWS Price List bulk offer. genai-prices does list them, under the Bedrock inference-profile ids rather than the ids we route on, so their Bedrock rows are mapped onto the regional profile a us./eu./apac. route is billed at. Their Azure and Vertex rows have no such entry anywhere and are hand-pinned — see dataQuality.pinnedPrices.", "Vertex AI publishes model availability in a table rendered client-side, so per-Region availability is not machine-readable. Vertex offers list the documented endpoint scopes (global, multi-region us/eu) instead." ], "failures": [], "gaps": [ { "model": "claude-fable-5-1", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-fable-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-haiku-4-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-4-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-4-6", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-4-7", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-4-8", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-5-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-opus-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-sonnet-4-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-sonnet-4-6", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-sonnet-5-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "claude-sonnet-5", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "deepseek-v3-2", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "gemini-3-pro", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "glm-5", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "gpt-5-4", "endpoint": "bedrock", "issue": "gov-cloud-only-price", "detail": "the only AWS Price List meters for \"openai.gpt-5.4\" are in GovCloud or an isolated Region, which price separately from the commercial list — no commercial on-demand price is published for this model yet" }, { "model": "gpt-5-4", "endpoint": "bedrock", "issue": "no-price", "detail": "no input or output price published for \"openai.gpt-5.4\"" }, { "model": "gpt-5-6-luna", "endpoint": "bedrock", "issue": "gov-cloud-only-price", "detail": "the only AWS Price List meters for \"openai.gpt-5.6-luna\" are in GovCloud or an isolated Region, which price separately from the commercial list — no commercial on-demand price is published for this model yet" }, { "model": "gpt-5-6-luna", "endpoint": "bedrock", "issue": "no-price", "detail": "no input or output price published for \"openai.gpt-5.6-luna\"" }, { "model": "gpt-5-6-terra", "endpoint": "bedrock", "issue": "gov-cloud-only-price", "detail": "the only AWS Price List meters for \"openai.gpt-5.6-terra\" are in GovCloud or an isolated Region, which price separately from the commercial list — no commercial on-demand price is published for this model yet" }, { "model": "gpt-5-6-terra", "endpoint": "bedrock", "issue": "no-price", "detail": "no input or output price published for \"openai.gpt-5.6-terra\"" }, { "model": "gpt-oss-120b", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "gpt-oss-20b", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "kimi-k2-thinking", "endpoint": "bedrock", "issue": "no-region-table", "detail": "\"Kimi K2 Thinking\" has no table on the Bedrock Regional-availability page" }, { "model": "kimi-k2-thinking", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "llama-4-maverick", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "llama-4-scout", "endpoint": "azure", "issue": "no-azure-meter-mapping", "detail": "this model is sold on Azure through Marketplace rather than a Foundry Models meter, so no per-profile prices are available — the headline price falls back to another source" }, { "model": "llama-4-scout", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "nova-2-pro", "endpoint": "bedrock", "issue": "no-region-table", "detail": "\"Nova 2 Pro\" has no table on the Bedrock Regional-availability page" }, { "model": "qwen3-235b-a22b", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" }, { "model": "qwen3-coder-480b", "endpoint": "vertex", "issue": "no-vertex-scopes", "detail": "no documented endpoint scopes found for this model" } ], "pinnedPrices": [ { "model": "claude-fable-5-1", "endpoint": "anthropic", "endpointModelId": "claude-fable-5-1", "detail": "verified 2026-09-08 against https://platform.claude.com/docs/en/about-claude/pricing: $10/$50, 5m cache write $12.50, cache hit $0.25 (Fable 5.1 reads at 0.025x base rather than the usual 0.1x), batch $5/$25. genai-prices carries no entry for this model." }, { "model": "claude-fable-5-1", "endpoint": "azure", "endpointModelId": "claude-fable-5-1", "detail": "verified 2026-09-08 against https://platform.claude.com/docs/en/about-claude/pricing: Claude in Microsoft Foundry meters Claude Consumption Units at the standard per-model Claude API rates. Anthropic models have no Azure Foundry retail meter." }, { "model": "claude-fable-5-1", "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-fable-5-1", "detail": "derived 2026-09-08: Anthropic's standard $10/$50 (https://platform.claude.com/docs/en/about-claude/pricing) plus the 10% premium Anthropic documents for regional and geo inference profiles — the same figures Google publishes today for its non-global Claude Fable 5.1 endpoints. Anthropic's catalogue is billed through Marketplace and is absent from the AWS Price List, and genai-prices has no entry for this model; verify against https://aws.amazon.com/bedrock/pricing/" }, { "model": "claude-fable-5-1", "endpoint": "vertex", "endpointModelId": "claude-fable-5-1", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint $10/$50, 5m cache write $12.50, cache hit $0.25, batch $5/$25; the non-global endpoints carry the documented 10% premium ($11/$55)" }, { "model": "claude-fable-5", "endpoint": "azure", "endpointModelId": "claude-fable-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-haiku-4-5", "endpoint": "azure", "endpointModelId": "claude-haiku-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-haiku-4-5", "endpoint": "vertex", "endpointModelId": "claude-haiku-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "claude-opus-4-5", "endpoint": "azure", "endpointModelId": "claude-opus-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-opus-4-5", "endpoint": "vertex", "endpointModelId": "claude-opus-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "claude-opus-4-6", "endpoint": "azure", "endpointModelId": "claude-opus-4-6", "detail": "verified 2026-09-08 against https://platform.claude.com/docs/en/about-claude/pricing: Claude in Microsoft Foundry meters Claude Consumption Units at the standard per-model Claude API rates ($5/$25, 5m cache write $6.25, cache hit $0.50). Anthropic models have no Azure Foundry retail meter." }, { "model": "claude-opus-4-7", "endpoint": "azure", "endpointModelId": "claude-opus-4-7", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-opus-4-8", "endpoint": "azure", "endpointModelId": "claude-opus-4-8", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-opus-5-5", "endpoint": "anthropic", "endpointModelId": "claude-opus-5-5", "detail": "verified 2026-09-29 against https://platform.claude.com/docs/en/about-claude/pricing: $4/$20, 5m cache write $5, cache hit $0.20 (Opus 5.5 reads at 0.05x base rather than the usual 0.1x), batch $2/$10. genai-prices carries no entry for this model." }, { "model": "claude-opus-5-5", "endpoint": "azure", "endpointModelId": "claude-opus-5-5", "detail": "verified 2026-09-29 against https://platform.claude.com/docs/en/about-claude/pricing: Claude in Microsoft Foundry meters Claude Consumption Units at the standard per-model Claude API rates. Anthropic models have no Azure Foundry retail meter." }, { "model": "claude-opus-5-5", "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-opus-5-5", "detail": "derived 2026-09-29: Anthropic's standard $4/$20 (https://platform.claude.com/docs/en/about-claude/pricing) plus the 10% premium Anthropic documents for regional and geo inference profiles, which is what the us. profile in this row is billed at. Anthropic's catalogue is billed through Marketplace and is absent from the AWS Price List, and genai-prices has no entry for this model; verify against https://aws.amazon.com/bedrock/pricing/" }, { "model": "claude-opus-5-5", "endpoint": "vertex", "endpointModelId": "claude-opus-5-5", "detail": "verified 2026-09-29 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint $4/$20, 5m cache write $5, cache hit $0.20; the non-global endpoints carry the documented 10% premium ($4.40/$22). Batch is left unpinned on purpose: Google's table states $2.50/$12.50, which is half of Claude Opus 5's base rather than half of Opus 5.5's own $4/$20, and Anthropic publishes $2/$10. Two sources disagree, so this row shows no batch price rather than the wrong one." }, { "model": "claude-opus-5", "endpoint": "azure", "endpointModelId": "claude-opus-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-sonnet-4-5", "endpoint": "azure", "endpointModelId": "claude-sonnet-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-sonnet-4-5", "endpoint": "vertex", "endpointModelId": "claude-sonnet-4-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "claude-sonnet-4-6", "endpoint": "azure", "endpointModelId": "claude-sonnet-4-6", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-sonnet-4-6", "endpoint": "vertex", "endpointModelId": "claude-sonnet-4-6", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "claude-sonnet-5-5", "endpoint": "anthropic", "endpointModelId": "claude-sonnet-5-5", "detail": "verified 2026-09-29 against https://platform.claude.com/docs/en/about-claude/pricing: $2/$10, 5m cache write $2.50, cache hit $0.20, batch $1/$5. genai-prices carries no entry for this model." }, { "model": "claude-sonnet-5-5", "endpoint": "azure", "endpointModelId": "claude-sonnet-5-5", "detail": "verified 2026-09-29 against https://platform.claude.com/docs/en/about-claude/pricing: Claude in Microsoft Foundry meters Claude Consumption Units at the standard per-model Claude API rates. Anthropic models have no Azure Foundry retail meter." }, { "model": "claude-sonnet-5-5", "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-5-5", "detail": "derived 2026-09-29: Anthropic's standard $2/$10 (https://platform.claude.com/docs/en/about-claude/pricing) plus the 10% premium Anthropic documents for regional and geo inference profiles, which is what the us. profile in this row is billed at. Anthropic's catalogue is billed through Marketplace and is absent from the AWS Price List, and genai-prices has no entry for this model; verify against https://aws.amazon.com/bedrock/pricing/" }, { "model": "claude-sonnet-5-5", "endpoint": "vertex", "endpointModelId": "claude-sonnet-5-5", "detail": "verified 2026-09-29 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint $2/$10, 5m cache write $2.50, cache hit $0.20, batch $1/$5; the non-global endpoints carry the documented 10% premium ($2.20/$11)" }, { "model": "claude-sonnet-5", "endpoint": "anthropic", "endpointModelId": "claude-sonnet-5", "detail": "verified 2026-09-08 against https://platform.claude.com/docs/en/about-claude/pricing: $2/$10 introductory price is now the standard price, the September 1 increase to $3/$15 did not happen; genai-prices still carries the cancelled $3/$15" }, { "model": "claude-sonnet-5", "endpoint": "azure", "endpointModelId": "claude-sonnet-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "claude-sonnet-5", "endpoint": "bedrock", "endpointModelId": "us.anthropic.claude-sonnet-5", "detail": "derived 2026-09-08: Anthropic standard $2/$10 (https://platform.claude.com/docs/en/about-claude/pricing) plus the 10% regional-endpoint premium Anthropic documents for Bedrock regional ids; genai-prices carries the cancelled $3.30/$16.50; verify against https://aws.amazon.com/bedrock/pricing/" }, { "model": "claude-sonnet-5", "endpoint": "vertex", "endpointModelId": "claude-sonnet-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "cohere-embed-v4", "endpoint": "bedrock", "endpointModelId": "cohere.embed-v4:0", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://aws.amazon.com/bedrock/pricing/" }, { "model": "deepseek-flash", "endpoint": "deepseek", "endpointModelId": "deepseek-flash", "detail": "verified 2026-09-29 against https://api-docs.deepseek.com/quick_start/pricing: the standard (peak) rate — $0.30 cache-miss input, $0.006 cache-hit input, $1.20 output. Off-peak is half of each, 01:00-04:00 and 06:00-10:00 UTC on weekdays, and a page that quotes one number cannot quote a price that depends on the hour. This model supersedes deepseek-v4-flash, which DeepSeek has retired; genai-prices still carries only the retired id. Cache writes are left unpriced because DeepSeek does not state a rate for them." }, { "model": "deepseek-v3-2", "endpoint": "vertex", "endpointModelId": "deepseek-ai/deepseek-v3.2-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "gemini-3-6-flash", "endpoint": "gemini", "endpointModelId": "gemini-3.6-flash", "detail": "verified 2026-09-08 against https://ai.google.dev/gemini-api/docs/pricing: introductory pricing in force through 2026-12-31. genai-prices already carries the $1.50/$7.50 rate that only applies from 2027-01-01." }, { "model": "gemini-3-6-flash", "endpoint": "vertex", "endpointModelId": "gemini-3.6-flash", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint, introductory pricing through 2026-12-31 (non-global $0.825/$4.125); genai-prices already carries the $1.50/$7.50 rate that only applies from 2027-01-01" }, { "model": "gemini-3-7-flash", "endpoint": "gemini", "endpointModelId": "gemini-3.7-flash", "detail": "verified 2026-09-08 against https://ai.google.dev/gemini-api/docs/pricing: introductory pricing in force through 2026-12-31; $1.50/$7.50 applies from 2027-01-01. genai-prices carries no entry for this model." }, { "model": "gemini-3-7-flash", "endpoint": "vertex", "endpointModelId": "gemini-3.7-flash", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint, introductory pricing through 2026-12-31 (non-global $0.825/$4.125); $1.50/$7.50 applies from 2027-01-01" }, { "model": "gemini-3-8-flash", "endpoint": "gemini", "endpointModelId": "gemini-3.8-flash", "detail": "verified 2026-09-08 against https://ai.google.dev/gemini-api/docs/pricing: introductory pricing in force through 2026-12-31; $1.50/$7.50 applies from 2027-01-01. genai-prices carries no entry for this model." }, { "model": "gemini-3-8-flash", "endpoint": "vertex", "endpointModelId": "gemini-3.8-flash", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing: global endpoint, introductory pricing through 2026-12-31 (non-global $0.825/$4.125); $1.50/$7.50 applies from 2027-01-01" }, { "model": "gemini-embedding-2", "endpoint": "gemini", "endpointModelId": "gemini-embedding-2", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://ai.google.dev/gemini-api/docs/pricing" }, { "model": "gemini-embedding-2", "endpoint": "vertex", "endpointModelId": "gemini-embedding-2", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "glm-5", "endpoint": "vertex", "endpointModelId": "zai-org/glm-5-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "gpt-5-6-luna", "endpoint": "openai", "endpointModelId": "gpt-5.6-luna", "detail": "verified 2026-09-08 against https://developers.openai.com/api/docs/pricing (short-context rate, up to 272K; $0.40/$1.80 above); genai-prices still lists $1/$6" }, { "model": "gpt-5-6-sol", "endpoint": "openai", "endpointModelId": "gpt-5.6-sol", "detail": "verified 2026-09-08 against https://developers.openai.com/api/docs/pricing (short-context rate, up to 272K; $8/$30 above; promotional price through at least 2026-11-21); genai-prices still lists $5/$30" }, { "model": "gpt-5-6-terra", "endpoint": "openai", "endpointModelId": "gpt-5.6-terra", "detail": "verified 2026-09-08 against https://developers.openai.com/api/docs/pricing (short-context rate, up to 272K; $4/$18 above); genai-prices still lists $2.50/$15" }, { "model": "gpt-6-astra", "endpoint": "openai", "endpointModelId": "gpt-6-astra", "detail": "verified 2026-09-29 against https://developers.openai.com/api/docs/pricing: $10 input / $1 cached input / $50 output, batch $5/$25. genai-prices carries no entry for this model. Azure meters it (see the offer below); AWS lists it on the Bedrock Regional-availability page but publishes no Price List meter for it, so there is no Bedrock row." }, { "model": "gpt-6-luna", "endpoint": "openai", "endpointModelId": "gpt-6-luna", "detail": "verified 2026-09-29 against https://developers.openai.com/api/docs/pricing: $0.10 input / $0.01 cached input / $0.50 output, batch $0.05/$0.25. genai-prices carries no entry for this model." }, { "model": "gpt-6-sol", "endpoint": "openai", "endpointModelId": "gpt-6-sol", "detail": "verified 2026-09-29 against https://developers.openai.com/api/docs/pricing: $2 input / $0.20 cached input / $10 output, batch $1/$5. genai-prices carries no entry for this model." }, { "model": "gpt-oss-120b", "endpoint": "vertex", "endpointModelId": "openai/gpt-oss-120b-maas", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "gpt-oss-20b", "endpoint": "vertex", "endpointModelId": "openai/gpt-oss-20b-maas", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "grok-4-1-fast", "endpoint": "vertex", "endpointModelId": "xai/grok-4.1-fast-reasoning", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "grok-4-6", "endpoint": "vertex", "endpointModelId": "xai/grok-4.6", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing: the up-to-200K-token rate; above 200K it is $4/$12" }, { "model": "grok-4-6", "endpoint": "xai", "endpointModelId": "grok-4.6", "detail": "verified 2026-09-08 against https://docs.x.ai/docs/models: the up-to-200K-token rate; requests above 200K input tokens bill at $4/$12 with a $1 cache hit. genai-prices carries no entry for this model." }, { "model": "grok-4-7", "endpoint": "xai", "endpointModelId": "grok-4.7", "detail": "verified 2026-09-29 against https://docs.x.ai/docs/models: the up-to-200K-token rate; requests above 200K input tokens bill at $4/$12 with a $1 cache hit. genai-prices carries no entry for this model." }, { "model": "kimi-k2-thinking", "endpoint": "vertex", "endpointModelId": "moonshotai/kimi-k2-thinking-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "llama-4-maverick", "endpoint": "vertex", "endpointModelId": "meta/llama-4-maverick-17b-128e-instruct-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "llama-4-scout", "endpoint": "azure", "endpointModelId": "Llama-4-Scout-17B-16E-Instruct", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://azure.microsoft.com/pricing/details/ai-foundry/" }, { "model": "llama-4-scout", "endpoint": "vertex", "endpointModelId": "meta/llama-4-scout-17b-16e-instruct-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "ministral-3-8b", "endpoint": "mistral", "endpointModelId": "ministral-3-8b-2512", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://mistral.ai/pricing" }, { "model": "mistral-large-3", "endpoint": "mistral", "endpointModelId": "mistral-large-3", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://mistral.ai/pricing" }, { "model": "mistral-medium-3-5", "endpoint": "mistral", "endpointModelId": "mistral-medium-3-5", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://mistral.ai/pricing" }, { "model": "qwen3-235b-a22b", "endpoint": "vertex", "endpointModelId": "qwen/qwen3-235b-a22b-instruct-2507-maas", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "qwen3-coder-480b", "endpoint": "vertex", "endpointModelId": "qwen/qwen3-coder-480b-a35b-instruct-maas", "detail": "verified 2026-09-08 against https://cloud.google.com/vertex-ai/generative-ai/pricing" }, { "model": "titan-embed-text-v2", "endpoint": "bedrock", "endpointModelId": "amazon.titan-embed-text-v2:0", "detail": "seeded 2026-08-14 from the retired fallback source; verify against https://aws.amazon.com/bedrock/pricing/" } ], "crossCheckedFields": 34, "crossCheck": [] } }