{ "kind": "inference-provider-index", "source": "OpenRouter public API (keyless): GET /api/v1/models and GET /api/v1/models/{author}/{slug}/endpoints", "fetchedAt": "2026-10-09T03:47:29.336Z", "finishedAt": "2026-10-09T03:48:11.235Z", "requests": 28, "note": "Third-party-reported keyless metadata. Unknown is not zero. Embedded maker rates are historical pins, not current vendor quotes. Ambiguous keys are excluded from history with explicit coverage.", "models": [ { "id": "anthropic/claude-haiku-4.5", "family": "Claude Haiku", "name": "Anthropic: Claude Haiku 4.5", "listedOnOpenRouter": true, "openRouterCreated": "2025-10-15T17:00:38.000Z", "contextLength": 200000, "openRouterListPrice": { "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1 }, "firstPartyListPrice": { "model": "claude-haiku-4-5", "input": 1, "output": 5, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:31.010Z" }, "endpoints": [ { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 75, "uptimeLast30m": 96, "uptimeLast1d": 92.82627484874676, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1.1, "outputUsdPerMTok": 5.5, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us-east5", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1.1, "outputUsdPerMTok": 5.5, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1.1, "outputUsdPerMTok": 5.5, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 200000, "maxCompletionTokens": 64000, "inputUsdPerMTok": 1.1, "outputUsdPerMTok": 5.5, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 87.85046728971963, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-sonnet-5", "family": "Claude Sonnet", "name": "Anthropic: Claude Sonnet 5", "listedOnOpenRouter": true, "openRouterCreated": "2026-06-30T18:11:23.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2 }, "firstPartyListPrice": { "model": "claude-sonnet-5", "input": 2, "output": 10, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:32.577Z" }, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-sonnet-5.5", "family": "Claude Sonnet", "name": "Anthropic: Claude Sonnet 5.5", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-28T18:04:46.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:34.128Z" }, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-opus-4.8", "family": "Claude Opus", "name": "Anthropic: Claude Opus 4.8", "listedOnOpenRouter": true, "openRouterCreated": "2026-05-27T18:04:51.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5 }, "firstPartyListPrice": { "model": "claude-opus-4-8", "input": 5, "output": 25, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:35.674Z" }, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-opus-5", "family": "Claude Opus", "name": "Anthropic: Claude Opus 5", "listedOnOpenRouter": true, "openRouterCreated": "2026-07-24T17:02:24.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5 }, "firstPartyListPrice": { "model": "claude-opus-5", "input": 5, "output": 25, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:37.212Z" }, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 27.5, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-opus-5.5", "family": "Claude Opus", "name": "Anthropic: Claude Opus 5.5", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-22T16:32:12.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2 }, "firstPartyListPrice": { "model": "claude-opus-5-5", "input": 4, "output": 20, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:38.757Z" }, "endpoints": [ { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 67.36111111111111, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4.4, "outputUsdPerMTok": 22, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4.4, "outputUsdPerMTok": 22, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 94.68085106382979, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4.4, "outputUsdPerMTok": 22, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4.4, "outputUsdPerMTok": 22, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4.4, "outputUsdPerMTok": 22, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 8, "outputUsdPerMTok": 40, "cacheReadUsdPerMTok": 0.4, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "anthropic/claude-fable-5.1", "family": "Claude Fable", "name": "Anthropic: Claude Fable 5.1", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-01T18:03:58.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 0.25 }, "firstPartyListPrice": { "model": "claude-fable-5-1", "input": 10, "output": 50, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:40.299Z" }, "endpoints": [ { "provider": "Azure", "tag": "azure", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 96.7741935483871, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Anthropic", "tag": "anthropic", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.75874547647769, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "openai/gpt-6-sol", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Sol", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-22T18:12:55.000Z", "contextLength": 1050000, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:41.853Z" }, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 1, "outputUsdPerMTok": 5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 10, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/eu", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 99.39024390243902, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 11, "cacheReadUsdPerMTok": 0.22, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 20, "cacheReadUsdPerMTok": 0.4, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "openai/gpt-6-luna", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Luna", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-22T18:13:06.000Z", "contextLength": 1050000, "openRouterListPrice": { "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.01 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:43.410Z" }, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.05, "outputUsdPerMTok": 0.25, "cacheReadUsdPerMTok": 0.005, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 84.30555555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.01, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.01, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.11, "outputUsdPerMTok": 0.55, "cacheReadUsdPerMTok": 0.011, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.27990617670055, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/eu", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.11, "outputUsdPerMTok": 0.55, "cacheReadUsdPerMTok": 0.011, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.11, "outputUsdPerMTok": 0.55, "cacheReadUsdPerMTok": 0.011, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.2, "outputUsdPerMTok": 1, "cacheReadUsdPerMTok": 0.02, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "openai/gpt-6-astra", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Astra", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-04T20:13:58.000Z", "contextLength": 1050000, "openRouterListPrice": { "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 1 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:44.964Z" }, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 25, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.79166666666667, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 10, "outputUsdPerMTok": 50, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-west-2", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 11, "outputUsdPerMTok": 55, "cacheReadUsdPerMTok": 1.1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 11, "outputUsdPerMTok": 55, "cacheReadUsdPerMTok": 1.1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 20, "outputUsdPerMTok": 100, "cacheReadUsdPerMTok": 2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai/ultrafast", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 60, "outputUsdPerMTok": 300, "cacheReadUsdPerMTok": 6, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "openai/gpt-5.5", "family": "OpenAI GPT", "name": "OpenAI: GPT-5.5", "listedOnOpenRouter": true, "openRouterCreated": "2026-04-24T17:31:33.000Z", "contextLength": 1050000, "openRouterListPrice": { "inputUsdPerMTok": 5, "outputUsdPerMTok": 30, "cacheReadUsdPerMTok": 0.5 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:46.525Z" }, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 2.5, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 30, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92248062015504, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "OpenAI", "tag": "openai", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5, "outputUsdPerMTok": 30, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 33, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/eu", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 33, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 5.5, "outputUsdPerMTok": 33, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": "unknown", "contextLength": 1050000, "maxCompletionTokens": 128000, "inputUsdPerMTok": 12.5, "outputUsdPerMTok": 75, "cacheReadUsdPerMTok": 1.25, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "openai/gpt-oss-120b", "family": "OpenAI open-weight", "name": "OpenAI: gpt-oss-120b", "listedOnOpenRouter": true, "openRouterCreated": "2025-08-05T17:17:11.000Z", "contextLength": 131072, "openRouterListPrice": { "inputUsdPerMTok": 0.037, "outputUsdPerMTok": 0.17, "cacheReadUsdPerMTok": "unknown" }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:48.087Z" }, "endpoints": [ { "provider": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.03, "outputUsdPerMTok": 0.17, "cacheReadUsdPerMTok": 0.03, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93055555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DekaLLM", "tag": "dekallm/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.03, "outputUsdPerMTok": 0.18, "cacheReadUsdPerMTok": 0.03, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.72222222222223, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.037, "outputUsdPerMTok": 0.17, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.02777777777779, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AkashML", "tag": "akashml/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.037, "outputUsdPerMTok": 0.187, "cacheReadUsdPerMTok": 0.037, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.79166666666667, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Crusoe", "tag": "crusoe/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.05, "outputUsdPerMTok": 0.25, "cacheReadUsdPerMTok": 0.05, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.80555555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.05, "outputUsdPerMTok": 0.25, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.56944444444444, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 32768, "inputUsdPerMTok": 0.05, "outputUsdPerMTok": 0.25, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93055555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 128000, "maxCompletionTokens": 4096, "inputUsdPerMTok": 0.06, "outputUsdPerMTok": 0.42, "cacheReadUsdPerMTok": 0.012, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.09, "outputUsdPerMTok": 0.36, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": -5, "uptimeLast5m": 0, "uptimeLast30m": 0, "uptimeLast1d": 18.055555555555554, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 128072, "maxCompletionTokens": 115264, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 128072, "maxCompletionTokens": 115264, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.75, "cacheReadUsdPerMTok": 0.055, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "SambaNova", "tag": "sambanova", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 0.95, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.64714184897672, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 96, "uptimeLast1d": 96.88605803255484, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/turbo", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 16384, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 8192, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": 0.075, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 80.75675675675676, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Phala", "tag": "phala", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 32768, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Together", "tag": "together", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.23579545454545, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Groq", "tag": "groq", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.6, "cacheReadUsdPerMTok": 0.075, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mara", "tag": "mara", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 117964, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.75, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 96.52042360060514, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Cerebras", "tag": "cerebras/fp16", "quantization": "fp16", "contextLength": 131072, "maxCompletionTokens": 40960, "inputUsdPerMTok": 0.35, "outputUsdPerMTok": 0.75, "cacheReadUsdPerMTok": 0.35, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "google/gemini-3.8-flash", "family": "Gemini Flash", "name": "Google: Gemini 3.8 Flash", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-02T15:14:16.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.75, "outputUsdPerMTok": 3.75, "cacheReadUsdPerMTok": 0.075 }, "firstPartyListPrice": { "model": "gemini-3.8-flash", "input": 0.75, "output": 3.75, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:49.617Z" }, "endpoints": [ { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.375, "outputUsdPerMTok": 1.875, "cacheReadUsdPerMTok": 0.0375, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.375, "outputUsdPerMTok": 1.875, "cacheReadUsdPerMTok": 0.0375, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.9758064516129, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.75, "outputUsdPerMTok": 3.75, "cacheReadUsdPerMTok": 0.075, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.75, "outputUsdPerMTok": 3.75, "cacheReadUsdPerMTok": 0.075, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 84.58333333333333, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1.35, "outputUsdPerMTok": 6.75, "cacheReadUsdPerMTok": 0.135, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.74248927038627, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1.35, "outputUsdPerMTok": 6.75, "cacheReadUsdPerMTok": 0.135, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true } ] }, { "id": "google/gemini-3.5-flash", "family": "Gemini Flash", "name": "Google: Gemini 3.5 Flash", "listedOnOpenRouter": true, "openRouterCreated": "2026-05-19T12:30:00.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 9, "cacheReadUsdPerMTok": 0.15 }, "firstPartyListPrice": { "model": "gemini-3.5-flash", "input": 1.5, "output": 9, "source": "Historical recorded maker list-price table; not refreshed by this API observation." }, "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:51.164Z" }, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.75, "outputUsdPerMTok": 4.5, "cacheReadUsdPerMTok": 0.075, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.75, "outputUsdPerMTok": 4.5, "cacheReadUsdPerMTok": 0.075, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 9, "cacheReadUsdPerMTok": 0.15, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.72222222222223, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 9, "cacheReadUsdPerMTok": 0.15, "discount": 0, "status": -2, "uptimeLast5m": 40, "uptimeLast30m": 83.33333333333334, "uptimeLast1d": 83.99443284620737, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1.65, "outputUsdPerMTok": 9.9, "cacheReadUsdPerMTok": 0.165, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 98.11320754716981, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 2.7, "outputUsdPerMTok": 16.2, "cacheReadUsdPerMTok": 0.27, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 2.7, "outputUsdPerMTok": 16.2, "cacheReadUsdPerMTok": 0.27, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true } ] }, { "id": "google/gemini-3.5-flash-lite", "family": "Gemini Flash", "name": "Google: Gemini 3.5 Flash Lite", "listedOnOpenRouter": true, "openRouterCreated": "2026-07-21T15:12:06.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.3, "outputUsdPerMTok": 2.5, "cacheReadUsdPerMTok": 0.03 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:52.711Z" }, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 1.25, "cacheReadUsdPerMTok": 0.015, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 1.25, "cacheReadUsdPerMTok": 0.015, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.3, "outputUsdPerMTok": 2.5, "cacheReadUsdPerMTok": 0.03, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.3, "outputUsdPerMTok": 2.5, "cacheReadUsdPerMTok": 0.03, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/eu", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.33, "outputUsdPerMTok": 2.75, "cacheReadUsdPerMTok": 0.033, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 99.35064935064936, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.33, "outputUsdPerMTok": 2.75, "cacheReadUsdPerMTok": 0.033, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.54, "outputUsdPerMTok": 4.5, "cacheReadUsdPerMTok": 0.054, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.54, "outputUsdPerMTok": 4.5, "cacheReadUsdPerMTok": 0.054, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true } ] }, { "id": "google/gemini-3.1-pro-preview", "family": "Gemini Pro", "name": "Google: Gemini 3.1 Pro Preview", "listedOnOpenRouter": true, "openRouterCreated": "2026-02-19T14:00:27.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.2 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:54.262Z" }, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": -2, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 92.48554913294798, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 1, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 2, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93055555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 2, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 3.6, "outputUsdPerMTok": 21.6, "cacheReadUsdPerMTok": 0.36, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 3.6, "outputUsdPerMTok": 21.6, "cacheReadUsdPerMTok": 0.36, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "meta-llama/llama-4-maverick", "family": "Llama", "name": "Meta: Llama 4 Maverick", "listedOnOpenRouter": true, "openRouterCreated": "2025-04-05T19:37:02.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.1875, "outputUsdPerMTok": 0.6525, "cacheReadUsdPerMTok": 0.05 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:55.811Z" }, "endpoints": [ { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 128000, "maxCompletionTokens": 16384, "inputUsdPerMTok": 0.1875, "outputUsdPerMTok": 0.6525, "cacheReadUsdPerMTok": 0.05, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.51388888888889, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 8192, "inputUsdPerMTok": 0.27, "outputUsdPerMTok": 0.85, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.36111111111111, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 524288, "maxCompletionTokens": 32768, "inputUsdPerMTok": 0.35, "outputUsdPerMTok": 1, "cacheReadUsdPerMTok": 0.17, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us-east5", "quantization": "unknown", "contextLength": 524288, "maxCompletionTokens": 8192, "inputUsdPerMTok": 0.35, "outputUsdPerMTok": 1.15, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "meta-llama/llama-3.3-70b-instruct", "family": "Llama", "name": "Meta: Llama 3.3 70B Instruct", "listedOnOpenRouter": true, "openRouterCreated": "2024-12-06T17:28:57.000Z", "contextLength": 131072, "openRouterListPrice": { "inputUsdPerMTok": 0.22, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.11 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:57.365Z" }, "endpoints": [ { "provider": "DeepInfra", "tag": "deepinfra/turbo", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 16384, "inputUsdPerMTok": 0.1, "outputUsdPerMTok": 0.32, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.86629526462396, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/bf16", "quantization": "bf16", "contextLength": 12288, "maxCompletionTokens": 11059, "inputUsdPerMTok": 0.135, "outputUsdPerMTok": 0.4, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.32016925246828, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.2, "outputUsdPerMTok": 0.52, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.13854989231874, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 16384, "inputUsdPerMTok": 0.22, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": 0.11, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Cloudflare", "tag": "cloudflare/fp8", "quantization": "fp8", "contextLength": 24000, "maxCompletionTokens": 21600, "inputUsdPerMTok": 0.293, "outputUsdPerMTok": 2.253, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.8567335243553, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "SambaNova", "tag": "sambanova-turbo", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 3072, "inputUsdPerMTok": 0.45, "outputUsdPerMTok": 0.9, "cacheReadUsdPerMTok": "unknown", "discount": 0.25, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.85915492957747, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Groq", "tag": "groq", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 32768, "inputUsdPerMTok": 0.59, "outputUsdPerMTok": 0.79, "cacheReadUsdPerMTok": 0.295, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "CoreWeave", "tag": "coreweave/fp16", "quantization": "fp16", "contextLength": 128000, "maxCompletionTokens": 115200, "inputUsdPerMTok": 0.71, "outputUsdPerMTok": 0.71, "cacheReadUsdPerMTok": 0.71, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.48867786705624, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex/us-central1", "quantization": "unknown", "contextLength": 128000, "maxCompletionTokens": 8192, "inputUsdPerMTok": 0.72, "outputUsdPerMTok": 0.72, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Google", "tag": "google-vertex", "quantization": "unknown", "contextLength": 128000, "maxCompletionTokens": 115200, "inputUsdPerMTok": 0.72, "outputUsdPerMTok": 0.72, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Together", "tag": "together", "quantization": "unknown", "contextLength": 131072, "maxCompletionTokens": 2048, "inputUsdPerMTok": 1.04, "outputUsdPerMTok": 1.04, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.43449575871819, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "deepseek/deepseek-v4-pro", "family": "DeepSeek", "name": "DeepSeek: DeepSeek V4 Pro 0423", "listedOnOpenRouter": true, "openRouterCreated": "2026-04-24T03:17:59.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.95526, "outputUsdPerMTok": 1.91052, "cacheReadUsdPerMTok": 0.079605 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:47:58.905Z" }, "endpoints": [ { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 0.3, "outputUsdPerMTok": 4.2, "cacheReadUsdPerMTok": 0.23, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.45, "outputUsdPerMTok": 3.48, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 93.10344827586206, "uptimeLast1d": 94.80427046263345, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "contextLength": 1024000, "maxCompletionTokens": 384000, "inputUsdPerMTok": 0.95526, "outputUsdPerMTok": 1.91052, "cacheReadUsdPerMTok": 0.079605, "discount": 0.451, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.957, "outputUsdPerMTok": 1.914, "cacheReadUsdPerMTok": 0.07975, "discount": 0.45, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 95.27777777777777, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 384000, "inputUsdPerMTok": 1.044, "outputUsdPerMTok": 2.088, "cacheReadUsdPerMTok": 0.2088, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Reka", "tag": "reka", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.05, "outputUsdPerMTok": 10.5, "cacheReadUsdPerMTok": 0.21, "discount": 0.3, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 90.62968515742129, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.15, "outputUsdPerMTok": 2.55, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.49892627057982, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 16384, "inputUsdPerMTok": 1.3, "outputUsdPerMTok": 2.6, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "contextLength": 1000000, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.416, "outputUsdPerMTok": 2.832, "cacheReadUsdPerMTok": 0.118, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.86111111111111, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.50162, "outputUsdPerMTok": 3.135, "cacheReadUsdPerMTok": 0.135, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.6, "outputUsdPerMTok": 3.2, "cacheReadUsdPerMTok": 0.135, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Venice", "tag": "venice", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 32768, "inputUsdPerMTok": 1.65, "outputUsdPerMTok": 3.301, "cacheReadUsdPerMTok": 0.33, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 94.56099456099456, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.68, "outputUsdPerMTok": 3.38, "cacheReadUsdPerMTok": 0.13, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.490538573508, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 1.69, "outputUsdPerMTok": 3.38, "cacheReadUsdPerMTok": 0.14, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 79.1885800150263, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 384000, "inputUsdPerMTok": 1.91, "outputUsdPerMTok": 3.83, "cacheReadUsdPerMTok": 0.16, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true } ] }, { "id": "deepseek/deepseek-v4-flash", "family": "DeepSeek", "name": "DeepSeek: DeepSeek V4 Flash 0423", "listedOnOpenRouter": true, "openRouterCreated": "2026-04-24T03:17:46.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.0057, "outputUsdPerMTok": 1.28, "cacheReadUsdPerMTok": 0.0057 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:00.441Z" }, "endpoints": [ { "provider": "OpenInference", "tag": "open-inference/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.00456, "outputUsdPerMTok": 0.280318, "cacheReadUsdPerMTok": 0.00456, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.35191637630662, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.03, "outputUsdPerMTok": 1.28, "cacheReadUsdPerMTok": 0.03, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Wafer", "tag": "wafer", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.035, "outputUsdPerMTok": 0.17, "cacheReadUsdPerMTok": 0.013, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.91666666666666, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "contextLength": 1024000, "maxCompletionTokens": 384000, "inputUsdPerMTok": 0.089306, "outputUsdPerMTok": 0.178612, "cacheReadUsdPerMTok": 0.017861, "discount": 0.3621, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.02777777777779, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 65536, "inputUsdPerMTok": 0.09, "outputUsdPerMTok": 0.18, "cacheReadUsdPerMTok": 0.018, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048575, "maxCompletionTokens": 943717, "inputUsdPerMTok": 0.091, "outputUsdPerMTok": 0.182, "cacheReadUsdPerMTok": 0.0182, "discount": 0.35, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 96.66666666666667, "uptimeLast1d": 99.58333333333333, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Venice", "tag": "venice", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 32768, "inputUsdPerMTok": 0.0966, "outputUsdPerMTok": 0.1925, "cacheReadUsdPerMTok": 0.0196, "discount": 0.3, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.44444444444444, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 384000, "inputUsdPerMTok": 0.098, "outputUsdPerMTok": 0.196, "cacheReadUsdPerMTok": 0.0196, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 0.13, "outputUsdPerMTok": 0.28, "cacheReadUsdPerMTok": 0.028, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "contextLength": 1000000, "maxCompletionTokens": 393216, "inputUsdPerMTok": 0.134, "outputUsdPerMTok": 0.268, "cacheReadUsdPerMTok": 0.0268, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 0.28, "cacheReadUsdPerMTok": 0.028, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.56944444444444, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 0.28, "cacheReadUsdPerMTok": 0.028, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.58333333333333, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 0.28, "cacheReadUsdPerMTok": 0.028, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.09722222222223, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 0.28, "cacheReadUsdPerMTok": 0.07, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93055555555556, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.19, "outputUsdPerMTok": 0.5, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.26651480637814, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Azure", "tag": "azure/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 384000, "inputUsdPerMTok": 0.21, "outputUsdPerMTok": 0.56, "cacheReadUsdPerMTok": 0.031, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 91.56716417910448, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "contextLength": 384000, "maxCompletionTokens": 345600, "inputUsdPerMTok": 0.44, "outputUsdPerMTok": 1.32, "cacheReadUsdPerMTok": 0.014, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.22752808988764, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "qwen/qwen3.8-max-0902", "family": "Qwen", "name": "Qwen: Qwen3.8 Max (0902)", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-03T21:08:24.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.25 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:01.976Z" }, "endpoints": [ { "provider": "Alibaba", "tag": "alibaba", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 131072, "inputUsdPerMTok": 2, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.25, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "qwen/qwen3.8-flash", "family": "Qwen", "name": "Qwen: Qwen3.8 Flash", "listedOnOpenRouter": true, "openRouterCreated": "2026-08-26T19:37:40.000Z", "contextLength": 1000000, "openRouterListPrice": { "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.47, "cacheReadUsdPerMTok": 0.016 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:03.514Z" }, "endpoints": [ { "provider": "Alibaba", "tag": "alibaba", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.15, "outputUsdPerMTok": 0.47, "cacheReadUsdPerMTok": 0.016, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": true } ] }, { "id": "mistralai/mistral-medium-3-5", "family": "Mistral", "name": "Mistral: Mistral Medium 3.5", "listedOnOpenRouter": true, "openRouterCreated": "2026-04-30T17:33:59.000Z", "contextLength": 262144, "openRouterListPrice": { "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 7.5, "cacheReadUsdPerMTok": "unknown" }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:05.059Z" }, "endpoints": [ { "provider": "Mistral", "tag": "mistral/zdr", "quantization": "unknown", "contextLength": 262144, "maxCompletionTokens": 209715, "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 7.5, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral", "quantization": "unknown", "contextLength": 262144, "maxCompletionTokens": 209715, "inputUsdPerMTok": 1.5, "outputUsdPerMTok": 7.5, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "contextLength": 262144, "maxCompletionTokens": 209715, "inputUsdPerMTok": 1.65, "outputUsdPerMTok": 8.25, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "mistralai/mistral-large-2512", "family": "Mistral", "name": "Mistral: Mistral Large 3 2512", "listedOnOpenRouter": true, "openRouterCreated": "2025-12-01T21:27:52.000Z", "contextLength": 262144, "openRouterListPrice": { "inputUsdPerMTok": 0.5, "outputUsdPerMTok": 1.5, "cacheReadUsdPerMTok": 0.05 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:06.592Z" }, "endpoints": [ { "provider": "Mistral", "tag": "mistral/zdr", "quantization": "unknown", "contextLength": 262144, "maxCompletionTokens": 209715, "inputUsdPerMTok": 0.5, "outputUsdPerMTok": 1.5, "cacheReadUsdPerMTok": 0.05, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral/eu", "quantization": "unknown", "contextLength": 262144, "maxCompletionTokens": 209715, "inputUsdPerMTok": 0.55, "outputUsdPerMTok": 1.65, "cacheReadUsdPerMTok": 0.055, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "x-ai/grok-4.7", "family": "Grok", "name": "SpaceXAI: Grok 4.7", "listedOnOpenRouter": true, "openRouterCreated": "2026-09-21T16:19:01.000Z", "contextLength": 500000, "openRouterListPrice": { "inputUsdPerMTok": 2, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.5 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:08.133Z" }, "endpoints": [ { "provider": "xAI", "tag": "xai/zdr", "quantization": "unknown", "contextLength": 500000, "maxCompletionTokens": 450000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "xAI", "tag": "xai", "quantization": "unknown", "contextLength": 500000, "maxCompletionTokens": 450000, "inputUsdPerMTok": 2, "outputUsdPerMTok": 6, "cacheReadUsdPerMTok": 0.5, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.72222222222223, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "xAI", "tag": "xai/zdr/us", "quantization": "unknown", "contextLength": 500000, "maxCompletionTokens": 450000, "inputUsdPerMTok": 2.2, "outputUsdPerMTok": 6.6, "cacheReadUsdPerMTok": 0.55, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "xAI", "tag": "xai/zdr/priority", "quantization": "unknown", "contextLength": 500000, "maxCompletionTokens": 450000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "xAI", "tag": "xai/priority", "quantization": "unknown", "contextLength": 500000, "maxCompletionTokens": 450000, "inputUsdPerMTok": 4, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 1, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": "unknown", "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] }, { "id": "moonshotai/kimi-k3", "family": "Kimi", "name": "MoonshotAI: Kimi K3", "listedOnOpenRouter": true, "openRouterCreated": "2026-07-16T15:30:58.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.58, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.3 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:09.686Z" }, "endpoints": [ { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.57, "outputUsdPerMTok": 13, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.58, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Wafer", "tag": "wafer", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.79, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.45, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.0271021542738, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.84, "outputUsdPerMTok": 13.5, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.53623188405797, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AkashML", "tag": "akashml/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.2, "outputUsdPerMTok": 14, "cacheReadUsdPerMTok": 1.2, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Makora", "tag": "makora/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.53, "outputUsdPerMTok": 12.75, "cacheReadUsdPerMTok": 0.204, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.20485744456178, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Decart", "tag": "decart/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.95, "outputUsdPerMTok": 9.75, "cacheReadUsdPerMTok": 0.195, "discount": 0.35, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.80749574105621, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Morph", "tag": "morph/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.5, "outputUsdPerMTok": 14, "cacheReadUsdPerMTok": 0.29, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.34587080948486, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Phala", "tag": "phala", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.55, "outputUsdPerMTok": 12.75, "cacheReadUsdPerMTok": 0.255, "discount": 0.15, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.55, "outputUsdPerMTok": 12.95, "cacheReadUsdPerMTok": 0.255, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.6, "outputUsdPerMTok": 13, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.74037788663401, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Together", "tag": "together", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.7, "outputUsdPerMTok": 13.5, "cacheReadUsdPerMTok": 0.27, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.04332634521313, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Wafer", "tag": "wafer/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.8, "outputUsdPerMTok": 14, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.69421487603306, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.85, "outputUsdPerMTok": 14.25, "cacheReadUsdPerMTok": 0.285, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.71473601260836, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "InferenceNet", "tag": "inference-net/fast", "quantization": "fp4", "contextLength": 250000, "maxCompletionTokens": 225000, "inputUsdPerMTok": 2.99, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.45, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92816091954023, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fast", "quantization": "fp4", "contextLength": 1000000, "maxCompletionTokens": 900000, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": -2, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-2", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 128000, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.99396378269618, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Chutes", "tag": "chutes/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 65535, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 74.35897435897436, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false }, { "provider": "Modal", "tag": "modal/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Fireworks", "tag": "fireworks", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Moonshot AI", "tag": "moonshotai/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 3, "outputUsdPerMTok": 15, "cacheReadUsdPerMTok": 0.3, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Alibaba", "tag": "alibaba", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 3.45, "outputUsdPerMTok": 17.25, "cacheReadUsdPerMTok": 0.345, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Fireworks", "tag": "fireworks/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 4.5, "outputUsdPerMTok": 22.5, "cacheReadUsdPerMTok": 0.45, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Fireworks", "tag": "fireworks/fast", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 4.5, "outputUsdPerMTok": 22.5, "cacheReadUsdPerMTok": 0.45, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 94.05940594059405, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": false, "supportsImplicitCaching": false } ] }, { "id": "z-ai/glm-5.3", "family": "GLM", "name": "Z.ai: GLM 5.3", "listedOnOpenRouter": true, "openRouterCreated": "2026-08-18T20:57:35.000Z", "contextLength": 1048576, "openRouterListPrice": { "inputUsdPerMTok": 0.039, "outputUsdPerMTok": 3.39, "cacheReadUsdPerMTok": 0.038 }, "firstPartyListPrice": "unknown: no historical first-party price", "endpointsFetch": { "status": 200, "fetchedAt": "2026-10-09T03:48:11.235Z" }, "endpoints": [ { "provider": "Relace", "tag": "relace", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.0312, "outputUsdPerMTok": 12, "cacheReadUsdPerMTok": 0.029, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Wafer", "tag": "wafer/us", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.039, "outputUsdPerMTok": 3.39, "cacheReadUsdPerMTok": 0.038, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.08, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.04, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Reka", "tag": "reka", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 4.2, "cacheReadUsdPerMTok": 0.105, "discount": 0.3, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.07112970711297, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Makora", "tag": "makora/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.14, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.1, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.65718349928876, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Morph", "tag": "morph/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.145, "outputUsdPerMTok": 3.74, "cacheReadUsdPerMTok": 0.108, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 94.40944881889763, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Wafer", "tag": "wafer", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.17, "outputUsdPerMTok": 3.39, "cacheReadUsdPerMTok": 0.16, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.19, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.19, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Sail Research", "tag": "sail-research/us", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.2, "outputUsdPerMTok": 3.4, "cacheReadUsdPerMTok": 0.15, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Sail Research", "tag": "sail-research/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.2, "outputUsdPerMTok": 3.4, "cacheReadUsdPerMTok": 0.15, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.5625, "outputUsdPerMTok": 2.5, "cacheReadUsdPerMTok": 0.125, "discount": 0.375, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.22905027932961, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Inceptron", "tag": "inceptron/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.6, "outputUsdPerMTok": 3.39, "cacheReadUsdPerMTok": 0.2, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.5179407176287, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 0.7, "outputUsdPerMTok": 2.2, "cacheReadUsdPerMTok": 0.13, "discount": 0.5, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92912827781714, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Phala", "tag": "phala", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.84, "outputUsdPerMTok": 2.64, "cacheReadUsdPerMTok": 0.156, "discount": 0.4, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Decart", "tag": "decart/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.8424, "outputUsdPerMTok": 2.6477, "cacheReadUsdPerMTok": 0.1955, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.72183588317107, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 128000, "inputUsdPerMTok": 0.91, "outputUsdPerMTok": 2.86, "cacheReadUsdPerMTok": 0.169, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.30357142857142, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 0.98, "outputUsdPerMTok": 3.08, "cacheReadUsdPerMTok": 0.182, "discount": 0.3, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 1.12, "outputUsdPerMTok": 3.52, "cacheReadUsdPerMTok": 0.208, "discount": 0.2, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.35948759007206, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Alibaba", "tag": "alibaba", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.19, "outputUsdPerMTok": 3.74, "cacheReadUsdPerMTok": 0.238, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Io Net", "tag": "io-net/fp8", "quantization": "fp8", "contextLength": 262124, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.2, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.36, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 96.78899082568807, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Friendli", "tag": "friendli", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.26, "outputUsdPerMTok": 3.96, "cacheReadUsdPerMTok": 0.234, "discount": 0.1, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.59718026183283, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral/zdr", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.14, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.73134328358208, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 99.29078014184397, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.14, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92383853769992, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral/nvfp4", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.14, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.27956989247312, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "contextLength": 1024000, "maxCompletionTokens": 921600, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": "unknown", "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 78.1725888324873, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Crusoe", "tag": "crusoe/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.86111111111111, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "PrimeIntellect", "tag": "primeintellect", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Venice", "tag": "venice", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0.2, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 96.84684684684684, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Together", "tag": "together", "quantization": "unknown", "contextLength": 1048575, "maxCompletionTokens": 943717, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 92.14285714285714, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.37722419928826, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Modal", "tag": "modal", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.14, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 99.72375690607734, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Fireworks", "tag": "fireworks", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 99.2462311557789, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 98.8477366255144, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.4, "outputUsdPerMTok": 4.4, "cacheReadUsdPerMTok": 0.26, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Mistral", "tag": "mistral/nvfp4", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "inputUsdPerMTok": 1.54, "outputUsdPerMTok": 4.84, "cacheReadUsdPerMTok": 0.154, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Fireworks", "tag": "fireworks/fast", "quantization": "unknown", "contextLength": 1048576, "maxCompletionTokens": 943718, "inputUsdPerMTok": 2.1, "outputUsdPerMTok": 6.6, "cacheReadUsdPerMTok": 0.39, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92673992673993, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 2.1, "outputUsdPerMTok": 6.6, "cacheReadUsdPerMTok": 0.21, "discount": 0, "status": 0, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.88925802879291, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "inputUsdPerMTok": 2.1, "outputUsdPerMTok": 6.6, "cacheReadUsdPerMTok": 0.21, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false }, { "provider": "Alibaba", "tag": "alibaba/fast", "quantization": "unknown", "contextLength": 1000000, "maxCompletionTokens": 131072, "inputUsdPerMTok": 2.8, "outputUsdPerMTok": 8.8, "cacheReadUsdPerMTok": 0.56, "discount": 0, "status": 0, "uptimeLast5m": "unknown", "uptimeLast30m": "unknown", "uptimeLast1d": 100, "latencyLast30m": "unknown", "throughputLast30m": "unknown", "supportsTools": true, "supportsImplicitCaching": false } ] } ] }