{ "note": "Inference provider index: every provider endpoint that OpenRouter’s public, keyless API listed for 27 curated models. Prices in USD per million tokens, as reported by the API. null = the API did not return the field.", "source": { "name": "OpenRouter public API (no key)", "url": "https://openrouter.ai/api/v1/models", "fetchedAt": "2026-10-06T12:35:07.924Z", "requests": 28 }, "fees": { "fetchedAt": "2026-10-06T12:35:54Z", "perRequestMarkup": 0, "creditFeePercent": { "standard": 5.5, "business": 8, "crypto": 5 }, "standardMinimum": "$0.80", "quote": "OpenRouter's fee is charged when you buy credits, 5.5% on Standard and 8% on Business, never on individual requests", "urls": [ "https://openrouter.ai/pricing", "https://openrouter.ai/docs/faq" ], "byok": "Standard and Business: $25,000 of list-price inference per month with no BYOK fee, 5% fee after." }, "live": { "status": "not measured", "reason": "not measured: no key in the environment. The live harness sends nothing without an OpenRouter key." }, "models": [ { "id": "anthropic/claude-haiku-4.5", "family": "Claude Haiku", "name": "Anthropic: Claude Haiku 4.5", "contextLength": 200000, "openRouterListPrice": { "input": 1, "output": 5, "cacheRead": 0.1 }, "firstParty": { "model": "claude-haiku-4-5", "vendor": "Anthropic", "input": 1, "output": 5, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1, "output": 5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.92517595342203, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1, "output": 5, "cacheRead": 0.1, "uptimeLast5m": 99.98413789456987, "uptimeLast30m": 99.96267403232429, "uptimeLast1d": 99.96316826699119, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1, "output": 5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 99.8421052631579, "uptimeLast1d": 99.6527903359977, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1, "output": 5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 99.98119151737434, "uptimeLast1d": 99.96502131918209, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1.1, "output": 5.5, "cacheRead": 0.11, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.87755102040816, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us-east5", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1.1, "output": 5.5, "cacheRead": 0.11, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1.1, "output": 5.5, "cacheRead": 0.11, "uptimeLast5m": 100, "uptimeLast30m": 98.49056603773585, "uptimeLast1d": 99.74146384951413, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 200000, "maxCompletionTokens": 64000, "input": 1.1, "output": 5.5, "cacheRead": 0.11, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-sonnet-5", "family": "Claude Sonnet", "name": "Anthropic: Claude Sonnet 5", "contextLength": 1000000, "openRouterListPrice": { "input": 2, "output": 10, "cacheRead": 0.2 }, "firstParty": { "model": "claude-sonnet-5", "vendor": "Anthropic", "input": 2, "output": 10, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9955166104812, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.74112989188366, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.98238816484678, "uptimeLast1d": 99.994504709464, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98873708284188, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98133814809113, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": 100, "uptimeLast30m": 99.91680532445923, "uptimeLast1d": 99.93635399302924, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-sonnet-5.5", "family": "Claude Sonnet", "name": "Anthropic: Claude Sonnet 5.5", "contextLength": 1000000, "openRouterListPrice": { "input": 2, "output": 10, "cacheRead": 0.2 }, "firstParty": { "model": "claude-sonnet-5-5", "vendor": "Anthropic", "input": 2, "output": 10, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.96046805819103, "uptimeLast1d": 99.99213568563714, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98162365240117, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99360253851272, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.99616659958215, "uptimeLast1d": 99.98163582797494, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.98889875666075, "uptimeLast1d": 99.97588565415644, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.99465469317938, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99761590667069, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-opus-4.8", "family": "Claude Opus", "name": "Anthropic: Claude Opus 4.8", "contextLength": 1000000, "openRouterListPrice": { "input": 5, "output": 25, "cacheRead": 0.5 }, "firstParty": { "model": "claude-opus-4-8", "vendor": "Anthropic", "input": 5, "output": 25, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99006250163445, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.13333333333333, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 94.89258208350223, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9717059156401, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98736829590882, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 1, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-opus-5", "family": "Claude Opus", "name": "Anthropic: Claude Opus 5", "contextLength": 1000000, "openRouterListPrice": { "input": 5, "output": 25, "cacheRead": 0.5 }, "firstParty": { "model": "claude-opus-5", "vendor": "Anthropic", "input": 5, "output": 25, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 99.63318588844535, "uptimeLast1d": 99.35074889685318, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": null, "uptimeLast30m": 99.40476190476191, "uptimeLast1d": 99.9691480453083, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 99.89146655813322, "uptimeLast1d": 99.9412432396341, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 99.92663242846662, "uptimeLast1d": 99.85869413007778, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": 98.7878787878788, "uptimeLast1d": 99.74137931034483, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 5.5, "output": 27.5, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 1, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-opus-5.5", "family": "Claude Opus", "name": "Anthropic: Claude Opus 5.5", "contextLength": 1000000, "openRouterListPrice": { "input": 4, "output": 20, "cacheRead": 0.2 }, "firstParty": { "model": "claude-opus-5-5", "vendor": "Anthropic", "input": 4, "output": 20, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.2, "uptimeLast5m": 99.96570644718793, "uptimeLast30m": 99.70002608468829, "uptimeLast1d": 97.21493261633232, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9916573971079, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.96418338108882, "uptimeLast1d": 99.95546325249522, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Claude Platform on AWS", "tag": "claude-on-aws", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.2, "uptimeLast5m": 99.95597299677137, "uptimeLast30m": 98.22593316646264, "uptimeLast1d": 99.91025474586137, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.2, "uptimeLast5m": 99.87080103359173, "uptimeLast30m": 99.87814784727863, "uptimeLast1d": 99.94455905793045, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4.4, "output": 22, "cacheRead": 0.22, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.90265271355561, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4.4, "output": 22, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.8426435877262, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4.4, "output": 22, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4.4, "output": 22, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/europe", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 4.4, "output": 22, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.98981635493398, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic/fast", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 8, "output": 40, "cacheRead": 0.4, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "anthropic/claude-fable-5.1", "family": "Claude Fable", "name": "Anthropic: Claude Fable 5.1", "contextLength": 1000000, "openRouterListPrice": { "input": 10, "output": 50, "cacheRead": 0.25 }, "firstParty": { "model": "claude-fable-5-1", "vendor": "Anthropic", "input": 10, "output": 50, "sourceId": "price-anthropic" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Azure", "tag": "azure", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 0.25, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.35897435897436, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Anthropic", "tag": "anthropic", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 0.25, "uptimeLast5m": 100, "uptimeLast30m": 99.90255310855584, "uptimeLast1d": 99.64788854065523, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 0.25, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 0.25, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.9194847020934, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "openai/gpt-6-sol", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Sol", "contextLength": 1050000, "openRouterListPrice": { "input": 2, "output": 10, "cacheRead": 0.2 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 1, "output": 5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99499687304565, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 100, "uptimeLast30m": 99.9950888910716, "uptimeLast1d": 99.99698135989736, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2, "output": 10, "cacheRead": 0.2, "uptimeLast5m": 99.95473064735174, "uptimeLast30m": 99.98333888703766, "uptimeLast1d": 99.99472332641503, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.98453687954229, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/eu", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2.2, "output": 11, "cacheRead": 0.22, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 4, "output": 20, "cacheRead": 0.4, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99109091719008, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "openai/gpt-6-luna", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Luna", "contextLength": 1050000, "openRouterListPrice": { "input": 0.1, "output": 0.5, "cacheRead": 0.01 }, "firstParty": { "model": "gpt-6-luna", "vendor": "OpenAI", "input": 0.1, "output": 0.5, "sourceId": "price-openai" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.05, "output": 0.25, "cacheRead": 0.005, "uptimeLast5m": 99.2446542627048, "uptimeLast30m": 99.81974375469068, "uptimeLast1d": 97.73924922356359, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.1, "output": 0.5, "cacheRead": 0.01, "uptimeLast5m": 100, "uptimeLast30m": 99.99054669719942, "uptimeLast1d": 99.98734489211762, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.1, "output": 0.5, "cacheRead": 0.01, "uptimeLast5m": 100, "uptimeLast30m": 99.95544893762852, "uptimeLast1d": 99.91915937300715, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.11, "output": 0.55, "cacheRead": 0.011, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98952628901458, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/eu", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.11, "output": 0.55, "cacheRead": 0.011, "uptimeLast5m": 100, "uptimeLast30m": 99.98882556710247, "uptimeLast1d": 99.97824662884547, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.11, "output": 0.55, "cacheRead": 0.011, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 98.79959466832958, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 0.2, "output": 1, "cacheRead": 0.02, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99216380182003, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "openai/gpt-6-astra", "family": "OpenAI GPT", "name": "OpenAI: GPT-6 Astra", "contextLength": 1050000, "openRouterListPrice": { "input": 10, "output": 50, "cacheRead": 1 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5, "output": 25, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99758838566535, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9743649781194, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 10, "output": 50, "cacheRead": 1, "uptimeLast5m": 100, "uptimeLast30m": 99.9902950310559, "uptimeLast1d": 99.98767810573345, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-west-2", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 11, "output": 55, "cacheRead": 1.1, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 11, "output": 55, "cacheRead": 1.1, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 20, "output": 100, "cacheRead": 2, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.96778869383154, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai/ultrafast", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 60, "output": 300, "cacheRead": 6, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "openai/gpt-5.5", "family": "OpenAI GPT", "name": "OpenAI: GPT-5.5", "contextLength": 1050000, "openRouterListPrice": { "input": 5, "output": 30, "cacheRead": 0.5 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "OpenAI", "tag": "openai/flex", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 2.5, "output": 15, "cacheRead": 0.25, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5, "output": 30, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.96428504295194, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5, "output": 30, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98993460453357, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5.5, "output": 33, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/eu", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5.5, "output": 33, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-1", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 5.5, "output": 33, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenAI", "tag": "openai/fast", "quantization": null, "contextLength": 1050000, "maxCompletionTokens": 128000, "input": 12.5, "output": 75, "cacheRead": 1.25, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "openai/gpt-oss-120b", "family": "OpenAI open-weight", "name": "OpenAI: gpt-oss-120b", "contextLength": 131072, "openRouterListPrice": { "input": 0.037, "output": 0.17, "cacheRead": null }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "CoreWeave", "tag": "coreweave/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.03, "output": 0.17, "cacheRead": 0.03, "uptimeLast5m": 99.65675057208237, "uptimeLast30m": 98.67733153443997, "uptimeLast1d": 98.77946107901673, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DekaLLM", "tag": "dekallm/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.03, "output": 0.18, "cacheRead": 0.03, "uptimeLast5m": 99.91859991859991, "uptimeLast30m": 99.59527507176809, "uptimeLast1d": 99.57271339742026, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.037, "output": 0.17, "cacheRead": null, "uptimeLast5m": 99.98530060267528, "uptimeLast30m": 99.97971547573971, "uptimeLast1d": 98.93315046661174, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AkashML", "tag": "akashml/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.037, "output": 0.187, "cacheRead": 0.037, "uptimeLast5m": 100, "uptimeLast30m": 99.97336316658676, "uptimeLast1d": 99.97984727380064, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.045, "output": 0.25, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 99.08734402852049, "uptimeLast1d": 98.57709391596141, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Crusoe", "tag": "crusoe/bf16", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.05, "output": 0.25, "cacheRead": 0.05, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98198937630497, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 32768, "input": 0.05, "output": 0.25, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 99.9672739173121, "uptimeLast1d": 98.56906715938703, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 128000, "maxCompletionTokens": 4096, "input": 0.06, "output": 0.42, "cacheRead": 0.012, "uptimeLast5m": 100, "uptimeLast30m": 99.97020040229458, "uptimeLast1d": 99.9766314873182, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.09, "output": 0.36, "cacheRead": null, "uptimeLast5m": 66.43990929705215, "uptimeLast30m": 72.48091192601355, "uptimeLast1d": 66.9305168386951, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 128072, "maxCompletionTokens": 115264, "input": 0.1, "output": 0.5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.95551252191662, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 128072, "maxCompletionTokens": 115264, "input": 0.1, "output": 0.5, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.97461092965169, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.1, "output": 0.75, "cacheRead": 0.055, "uptimeLast5m": 100, "uptimeLast30m": 99.97040982393845, "uptimeLast1d": 99.88140271955834, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SambaNova", "tag": "sambanova", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.14, "output": 0.95, "cacheRead": null, "uptimeLast5m": 99.61464354527938, "uptimeLast30m": 99.7148288973384, "uptimeLast1d": 99.68209019021158, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/eu-west-1", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.96718083360683, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 98.40146750524109, "uptimeLast1d": 97.2963707478223, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.45987434971715, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/turbo", "quantization": "bf16", "contextLength": 131072, "maxCompletionTokens": 16384, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.98147356420122, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 8192, "input": 0.15, "output": 0.6, "cacheRead": 0.075, "uptimeLast5m": 85.97560975609755, "uptimeLast30m": 98.09210526315789, "uptimeLast1d": 83.35103060587133, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Phala", "tag": "phala", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 32768, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.26864359363759, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Together", "tag": "together", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.15, "output": 0.6, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": 72.79713114754098, "uptimeLast1d": 87.16544928807335, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Groq", "tag": "groq", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 65536, "input": 0.15, "output": 0.6, "cacheRead": 0.075, "uptimeLast5m": 99.31056095267941, "uptimeLast30m": 99.08905797878042, "uptimeLast1d": 99.34153652532547, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mara", "tag": "mara", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 117964, "input": 0.15, "output": 0.75, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 99.95460735360872, "uptimeLast1d": 96.56076427460565, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Cerebras", "tag": "cerebras/fp16", "quantization": "fp16", "contextLength": 131072, "maxCompletionTokens": 40960, "input": 0.35, "output": 0.75, "cacheRead": 0.35, "uptimeLast5m": 100, "uptimeLast30m": 99.99268792044458, "uptimeLast1d": 99.98132589495438, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "google/gemini-3.8-flash", "family": "Gemini Flash", "name": "Google: Gemini 3.8 Flash", "contextLength": 1048576, "openRouterListPrice": { "input": 0.75, "output": 3.75, "cacheRead": 0.075 }, "firstParty": { "model": "gemini-3.8-flash", "vendor": "Google", "input": 0.75, "output": 3.75, "sourceId": "price-google" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.375, "output": 1.875, "cacheRead": 0.0375, "uptimeLast5m": 100, "uptimeLast30m": 99.88803045571605, "uptimeLast1d": 99.930206084305, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.375, "output": 1.875, "cacheRead": 0.0375, "uptimeLast5m": 100, "uptimeLast30m": 99.81735159817352, "uptimeLast1d": 99.43995283813373, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.75, "output": 3.75, "cacheRead": 0.075, "uptimeLast5m": 99.73287540545698, "uptimeLast30m": 99.38585345192715, "uptimeLast1d": 99.8317977679604, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.75, "output": 3.75, "cacheRead": 0.075, "uptimeLast5m": 98.07447669712039, "uptimeLast30m": 98.10880640706256, "uptimeLast1d": 97.48711959693408, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1.35, "output": 6.75, "cacheRead": 0.135, "uptimeLast5m": 100, "uptimeLast30m": 99.96811224489795, "uptimeLast1d": 99.7129647888867, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1.35, "output": 6.75, "cacheRead": 0.135, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.75418102361543, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "google/gemini-3.5-flash", "family": "Gemini Flash", "name": "Google: Gemini 3.5 Flash", "contextLength": 1048576, "openRouterListPrice": { "input": 1.5, "output": 9, "cacheRead": 0.15 }, "firstParty": { "model": "gemini-3.5-flash", "vendor": "Google", "input": 1.5, "output": 9, "sourceId": "price-google" }, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.75, "output": 4.5, "cacheRead": 0.075, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.78948922350162, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.75, "output": 4.5, "cacheRead": 0.075, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.96366662369171, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1.5, "output": 9, "cacheRead": 0.15, "uptimeLast5m": 99.53186892329853, "uptimeLast30m": 99.22730422730423, "uptimeLast1d": 98.72364763354202, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1.5, "output": 9, "cacheRead": 0.15, "uptimeLast5m": 99.40119760479041, "uptimeLast30m": 99.68494013862635, "uptimeLast1d": 99.89589047229903, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1.65, "output": 9.9, "cacheRead": 0.165, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 2.7, "output": 16.2, "cacheRead": 0.27, "uptimeLast5m": 100, "uptimeLast30m": null, "uptimeLast1d": 99.89841527834213, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 2.7, "output": 16.2, "cacheRead": 0.27, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93347272381676, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "google/gemini-3.5-flash-lite", "family": "Gemini Flash", "name": "Google: Gemini 3.5 Flash Lite", "contextLength": 1048576, "openRouterListPrice": { "input": 0.3, "output": 2.5, "cacheRead": 0.03 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.15, "output": 1.25, "cacheRead": 0.015, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.99112426035502, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.15, "output": 1.25, "cacheRead": 0.015, "uptimeLast5m": 100, "uptimeLast30m": 99.99567679737149, "uptimeLast1d": 99.98352646296478, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.3, "output": 2.5, "cacheRead": 0.03, "uptimeLast5m": 99.98916224124851, "uptimeLast30m": 99.9966212791837, "uptimeLast1d": 99.94880507598998, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.3, "output": 2.5, "cacheRead": 0.03, "uptimeLast5m": 99.94015201388473, "uptimeLast30m": 99.93661065073128, "uptimeLast1d": 99.95057370008466, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/eu", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.33, "output": 2.75, "cacheRead": 0.033, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.33, "output": 2.75, "cacheRead": 0.033, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.86423584173778, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.54, "output": 4.5, "cacheRead": 0.054, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.95271770413618, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.54, "output": 4.5, "cacheRead": 0.054, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.95570517363572, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "google/gemini-3.1-pro-preview", "family": "Gemini Pro", "name": "Google: Gemini 3.1 Pro Preview", "contextLength": 1048576, "openRouterListPrice": { "input": 2, "output": 12, "cacheRead": 0.2 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Google", "tag": "google-vertex/global/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1, "output": 6, "cacheRead": 0.1, "uptimeLast5m": null, "uptimeLast30m": 99.01960784313727, "uptimeLast1d": 93.18955109208649, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/flex", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 1, "output": 6, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.96735759751918, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 2, "output": 12, "cacheRead": 0.2, "uptimeLast5m": 98.58776727996022, "uptimeLast30m": 97.91647012843492, "uptimeLast1d": 97.9970626645471, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 2, "output": 12, "cacheRead": 0.2, "uptimeLast5m": 99.64912280701755, "uptimeLast30m": 99.97098084735926, "uptimeLast1d": 99.81297894003536, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/global/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 3.6, "output": 21.6, "cacheRead": 0.36, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.87261146496816, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google AI Studio", "tag": "google-ai-studio/priority", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 3.6, "output": 21.6, "cacheRead": 0.36, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.90243902439025, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "meta-llama/llama-4-maverick", "family": "Llama", "name": "Meta: Llama 4 Maverick", "contextLength": 1048576, "openRouterListPrice": { "input": 0.1875, "output": 0.6525, "cacheRead": null }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 128000, "maxCompletionTokens": 16384, "input": 0.1875, "output": 0.6525, "cacheRead": null, "uptimeLast5m": 0, "uptimeLast30m": 61.66148784500092, "uptimeLast1d": 99.29659007546566, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 8192, "input": 0.27, "output": 0.85, "cacheRead": null, "uptimeLast5m": 99.01055408970977, "uptimeLast30m": 97.44097084817307, "uptimeLast1d": 97.57527071225398, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 524288, "maxCompletionTokens": 32768, "input": 0.35, "output": 1, "cacheRead": 0.17, "uptimeLast5m": 98.32167832167832, "uptimeLast30m": 99.57285239677266, "uptimeLast1d": 99.86552491086903, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us-east5", "quantization": null, "contextLength": 524288, "maxCompletionTokens": 8192, "input": 0.35, "output": 1.15, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "meta-llama/llama-3.3-70b-instruct", "family": "Llama", "name": "Meta: Llama 3.3 70B Instruct", "contextLength": 131072, "openRouterListPrice": { "input": 0.22, "output": 0.5, "cacheRead": 0.11 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "DeepInfra", "tag": "deepinfra/turbo", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 16384, "input": 0.1, "output": 0.32, "cacheRead": null, "uptimeLast5m": 99.81268397109982, "uptimeLast30m": 99.06452286489873, "uptimeLast1d": 98.10395426356287, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/bf16", "quantization": "bf16", "contextLength": 12288, "maxCompletionTokens": 11059, "input": 0.135, "output": 0.4, "cacheRead": null, "uptimeLast5m": 99.69788519637463, "uptimeLast30m": 99.53885174083467, "uptimeLast1d": 98.07529349645078, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 128000, "input": 0.2, "output": 0.52, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 99.91784760731156, "uptimeLast1d": 99.26920268442856, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 131072, "maxCompletionTokens": 16384, "input": 0.22, "output": 0.5, "cacheRead": 0.11, "uptimeLast5m": 99.74683544303798, "uptimeLast30m": 99.60431809384542, "uptimeLast1d": 99.65089343634655, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Cloudflare", "tag": "cloudflare/fp8", "quantization": "fp8", "contextLength": 24000, "maxCompletionTokens": 21600, "input": 0.293, "output": 2.253, "cacheRead": null, "uptimeLast5m": 98.92125134843582, "uptimeLast30m": 99.26171079429736, "uptimeLast1d": 98.84870252812117, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SambaNova", "tag": "sambanova-turbo", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 3072, "input": 0.45, "output": 0.9, "cacheRead": null, "uptimeLast5m": 99.68652037617555, "uptimeLast30m": 99.64476021314387, "uptimeLast1d": 98.56062021744026, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Groq", "tag": "groq", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 32768, "input": 0.59, "output": 0.79, "cacheRead": 0.295, "uptimeLast5m": 99.68394437420986, "uptimeLast30m": 99.88660417296643, "uptimeLast1d": 99.85338863179534, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "CoreWeave", "tag": "coreweave/fp16", "quantization": "fp16", "contextLength": 128000, "maxCompletionTokens": 115200, "input": 0.71, "output": 0.71, "cacheRead": 0.71, "uptimeLast5m": 99.2836676217765, "uptimeLast30m": 99.8329435349148, "uptimeLast1d": 97.71678589838692, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex/us-central1", "quantization": null, "contextLength": 128000, "maxCompletionTokens": 8192, "input": 0.72, "output": 0.72, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Google", "tag": "google-vertex", "quantization": null, "contextLength": 128000, "maxCompletionTokens": 115200, "input": 0.72, "output": 0.72, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": null, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Together", "tag": "together", "quantization": null, "contextLength": 131072, "maxCompletionTokens": 2048, "input": 1.04, "output": 1.04, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 99.7364953886693, "uptimeLast1d": 93.22430722996819, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "deepseek/deepseek-v4-pro", "family": "DeepSeek", "name": "DeepSeek: DeepSeek V4 Pro 0423", "contextLength": 1048576, "openRouterListPrice": { "input": 0.2088, "output": 0.4176, "cacheRead": 0.0174 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 0.2067, "output": 4.2, "cacheRead": 0.21, "uptimeLast5m": 99.9634636463281, "uptimeLast30m": 99.88587873375012, "uptimeLast1d": 99.89784249082496, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "contextLength": 1024000, "maxCompletionTokens": 384000, "input": 0.2088, "output": 0.4176, "cacheRead": 0.0174, "uptimeLast5m": 99.85149183205077, "uptimeLast30m": 99.62698890680551, "uptimeLast1d": 98.6742503953199, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.45, "output": 3.48, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 99.67105263157895, "uptimeLast1d": 98.29912171910198, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Reka", "tag": "reka", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 0.9, "output": 9, "cacheRead": 0.18, "uptimeLast5m": 100, "uptimeLast30m": 91.13924050632912, "uptimeLast1d": 98.82655687081832, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.957, "output": 1.914, "cacheRead": 0.07975, "uptimeLast5m": 85.71428571428571, "uptimeLast30m": 94.08244680851064, "uptimeLast1d": 97.0456429896948, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 384000, "input": 1.044, "output": 2.088, "cacheRead": 0.2088, "uptimeLast5m": 98.34710743801654, "uptimeLast30m": 98.98897058823529, "uptimeLast1d": 99.53668074947778, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.15, "output": 2.55, "cacheRead": 0.2, "uptimeLast5m": 99.06542056074767, "uptimeLast30m": 98.89589905362776, "uptimeLast1d": 98.29282192323893, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 16384, "input": 1.3, "output": 2.6, "cacheRead": 0.1, "uptimeLast5m": 100, "uptimeLast30m": 99.9117387466902, "uptimeLast1d": 99.81416957026713, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "contextLength": 1000000, "maxCompletionTokens": 393216, "input": 1.416, "output": 2.832, "cacheRead": 0.118, "uptimeLast5m": 99.12280701754386, "uptimeLast30m": 99.35275080906149, "uptimeLast1d": 90.11451942740287, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 1.50162, "output": 3.135, "cacheRead": 0.135, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.20689610338954, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 1.6, "output": 3.2, "cacheRead": 0.135, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93592876147038, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Venice", "tag": "venice", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 32768, "input": 1.65, "output": 3.301, "cacheRead": 0.33, "uptimeLast5m": 100, "uptimeLast30m": 99.9074074074074, "uptimeLast1d": 97.05384354893329, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 1.68, "output": 3.38, "cacheRead": 0.13, "uptimeLast5m": 100, "uptimeLast30m": 98.73417721518987, "uptimeLast1d": 99.00532419827479, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 1.69, "output": 3.38, "cacheRead": 0.14, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.96175147639302, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "NextBit", "tag": "nextbit/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.74, "output": 3.48, "cacheRead": 0.145, "uptimeLast5m": 100, "uptimeLast30m": 99.01234567901234, "uptimeLast1d": 98.70894996476392, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 384000, "input": 1.91, "output": 3.83, "cacheRead": 0.16, "uptimeLast5m": 100, "uptimeLast30m": 99.89462592202318, "uptimeLast1d": 99.19957624624801, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "deepseek/deepseek-v4-flash", "family": "DeepSeek", "name": "DeepSeek: DeepSeek V4 Flash 0423", "contextLength": 1048576, "openRouterListPrice": { "input": 0.012, "output": 1.28, "cacheRead": 0.012 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.012, "output": 1.28, "cacheRead": 0.012, "uptimeLast5m": 99.92836676217765, "uptimeLast30m": 99.85392767832334, "uptimeLast1d": 99.92051702497406, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "OpenInference", "tag": "open-inference/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.0132, "output": 1.408, "cacheRead": 0.0132, "uptimeLast5m": 99.63133640552996, "uptimeLast30m": 99.6698749244432, "uptimeLast1d": 99.07939241057824, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "StreamLake", "tag": "streamlake/fp8", "quantization": "fp8", "contextLength": 1024000, "maxCompletionTokens": 384000, "input": 0.042, "output": 0.084, "cacheRead": 0.0084, "uptimeLast5m": 99.61044912923923, "uptimeLast30m": 99.57132706570441, "uptimeLast1d": 99.11884665759047, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 65536, "input": 0.09, "output": 0.18, "cacheRead": 0.018, "uptimeLast5m": 99.959505972869, "uptimeLast30m": 99.75266731328807, "uptimeLast1d": 99.66598206550182, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048575, "maxCompletionTokens": 943717, "input": 0.091, "output": 0.182, "cacheRead": 0.0182, "uptimeLast5m": 99.99699121434588, "uptimeLast30m": 99.99597493187572, "uptimeLast1d": 99.98364648861408, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Venice", "tag": "venice", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 32768, "input": 0.0966, "output": 0.1925, "cacheRead": 0.0196, "uptimeLast5m": 99.29577464788733, "uptimeLast30m": 99.47358526038728, "uptimeLast1d": 96.1447601515689, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 384000, "input": 0.098, "output": 0.196, "cacheRead": 0.0196, "uptimeLast5m": 99.85272459499264, "uptimeLast30m": 99.71518086015381, "uptimeLast1d": 99.7483518152481, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 0.13, "output": 0.28, "cacheRead": 0.028, "uptimeLast5m": 100, "uptimeLast30m": 99.85331098072086, "uptimeLast1d": 99.54294023906091, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Alibaba", "tag": "alibaba/fp8", "quantization": "fp8", "contextLength": 1000000, "maxCompletionTokens": 393216, "input": 0.134, "output": 0.268, "cacheRead": 0.0268, "uptimeLast5m": 99.35073539154631, "uptimeLast30m": 99.37517965476029, "uptimeLast1d": 99.20936195212946, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 0.14, "output": 0.28, "cacheRead": 0.028, "uptimeLast5m": 99.96985530546624, "uptimeLast30m": 98.83424682003216, "uptimeLast1d": 99.41426754843337, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 0.14, "output": 0.28, "cacheRead": 0.028, "uptimeLast5m": 99.98098497813272, "uptimeLast30m": 99.81632757912043, "uptimeLast1d": 99.86862969086607, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 393216, "input": 0.14, "output": 0.28, "cacheRead": 0.028, "uptimeLast5m": 99.78700745473908, "uptimeLast30m": 99.63212327340875, "uptimeLast1d": 99.09036835004135, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.14, "output": 0.28, "cacheRead": 0.07, "uptimeLast5m": 99.96275208854361, "uptimeLast30m": 99.9617573524574, "uptimeLast1d": 99.6805974341051, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mancer 2", "tag": "mancer/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.19, "output": 0.5, "cacheRead": null, "uptimeLast5m": 97.38903394255874, "uptimeLast30m": 99.2626404494382, "uptimeLast1d": 94.91075919462268, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Azure", "tag": "azure/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 384000, "input": 0.21, "output": 0.56, "cacheRead": 0.031, "uptimeLast5m": 100, "uptimeLast30m": 97.31253444110041, "uptimeLast1d": 95.28336434538186, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": null, "contextLength": 384000, "maxCompletionTokens": 345600, "input": 0.44, "output": 1.32, "cacheRead": 0.014, "uptimeLast5m": 100, "uptimeLast30m": 99.48275862068967, "uptimeLast1d": 98.12890437289764, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "qwen/qwen3.8-max-0902", "family": "Qwen", "name": "Qwen: Qwen3.8 Max (0902)", "contextLength": 1000000, "openRouterListPrice": { "input": 2, "output": 6, "cacheRead": 0.25 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Alibaba", "tag": "alibaba", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 131072, "input": 2, "output": 6, "cacheRead": 0.25, "uptimeLast5m": 99.60861056751467, "uptimeLast30m": 99.78917105893628, "uptimeLast1d": 99.79887422450065, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "qwen/qwen3.8-flash", "family": "Qwen", "name": "Qwen: Qwen3.8 Flash", "contextLength": 1000000, "openRouterListPrice": { "input": 0.15, "output": 0.47, "cacheRead": 0.016 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Alibaba", "tag": "alibaba", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 131072, "input": 0.15, "output": 0.47, "cacheRead": 0.016, "uptimeLast5m": 99.30452061599603, "uptimeLast30m": 99.0924143964009, "uptimeLast1d": 98.69670761956951, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "mistralai/mistral-medium-3-5", "family": "Mistral", "name": "Mistral: Mistral Medium 3.5", "contextLength": 262144, "openRouterListPrice": { "input": 1.5, "output": 7.5, "cacheRead": null }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Mistral", "tag": "mistral/zdr", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 209715, "input": 1.5, "output": 7.5, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.91462373460178, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 209715, "input": 1.5, "output": 7.5, "cacheRead": null, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.93352470161656, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral/eu", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 209715, "input": 1.65, "output": 8.25, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "mistralai/mistral-large-2512", "family": "Mistral", "name": "Mistral: Mistral Large 3 2512", "contextLength": 262144, "openRouterListPrice": { "input": 0.5, "output": 1.5, "cacheRead": 0.05 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Mistral", "tag": "mistral/zdr", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 209715, "input": 0.5, "output": 1.5, "cacheRead": 0.05, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.85370299309287, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral/eu", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 209715, "input": 0.55, "output": 1.65, "cacheRead": 0.055, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.84310885831523, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "x-ai/grok-4.7", "family": "Grok", "name": "SpaceXAI: Grok 4.7", "contextLength": 500000, "openRouterListPrice": { "input": 2, "output": 6, "cacheRead": 0.5 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "xAI", "tag": "xai/zdr", "quantization": null, "contextLength": 500000, "maxCompletionTokens": 450000, "input": 2, "output": 6, "cacheRead": 0.5, "uptimeLast5m": 100, "uptimeLast30m": 99.96322177271055, "uptimeLast1d": 99.45653287438277, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "xAI", "tag": "xai", "quantization": null, "contextLength": 500000, "maxCompletionTokens": 450000, "input": 2, "output": 6, "cacheRead": 0.5, "uptimeLast5m": 99.58677685950413, "uptimeLast30m": 99.68156922685009, "uptimeLast1d": 99.32491064993896, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "xAI", "tag": "xai/zdr/us", "quantization": null, "contextLength": 500000, "maxCompletionTokens": 450000, "input": 2.2, "output": 6.6, "cacheRead": 0.55, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "xAI", "tag": "xai/zdr/priority", "quantization": null, "contextLength": 500000, "maxCompletionTokens": 450000, "input": 4, "output": 12, "cacheRead": 1, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.55290611028316, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "xAI", "tag": "xai/priority", "quantization": null, "contextLength": 500000, "maxCompletionTokens": 450000, "input": 4, "output": 12, "cacheRead": 1, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.37888198757764, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "moonshotai/kimi-k3", "family": "Kimi", "name": "MoonshotAI: Kimi K3", "contextLength": 1048576, "openRouterListPrice": { "input": 0.95, "output": 14, "cacheRead": 0.31 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Relace", "tag": "relace/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.83, "output": 13, "cacheRead": 0.45, "uptimeLast5m": 99.71070395371264, "uptimeLast30m": 99.73149661452253, "uptimeLast1d": 99.65886244244115, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Sail Research", "tag": "sail-research/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.84, "output": 13.5, "cacheRead": 0.3, "uptimeLast5m": 100, "uptimeLast30m": 99.98619832999793, "uptimeLast1d": 99.90188805666563, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "InferenceNet", "tag": "inference-net/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.95, "output": 14, "cacheRead": 0.31, "uptimeLast5m": 100, "uptimeLast30m": 99.91522550016954, "uptimeLast1d": 99.8987269563208, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Wafer", "tag": "wafer", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.95, "output": 14, "cacheRead": 0.4, "uptimeLast5m": 98.88888888888889, "uptimeLast30m": 99.2651561543172, "uptimeLast1d": 99.47745009306853, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Morph", "tag": "morph/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.274, "output": 13.296, "cacheRead": 0.278, "uptimeLast5m": 100, "uptimeLast30m": 99.82547993019197, "uptimeLast1d": 99.55815054442165, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AkashML", "tag": "akashml/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.3, "output": 14, "cacheRead": 1.3, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.41991341991341, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Makora", "tag": "makora", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.53, "output": 12.75, "cacheRead": 0.204, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 96.98536692705468, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Phala", "tag": "phala", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.95, "output": 9.75, "cacheRead": 0.195, "uptimeLast5m": 99.66442953020133, "uptimeLast30m": 99.26722032242306, "uptimeLast1d": 97.00536861378048, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Decart", "tag": "decart/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.01, "output": 10.05, "cacheRead": 0.201, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 86.93045563549161, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.55, "output": 12.95, "cacheRead": 0.255, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.92344497607655, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Together", "tag": "together", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.7, "output": 13.5, "cacheRead": 0.27, "uptimeLast5m": 99.70326409495549, "uptimeLast30m": 99.29538290376414, "uptimeLast1d": 99.31661952479296, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Wafer", "tag": "wafer/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.8, "output": 14, "cacheRead": 0.3, "uptimeLast5m": 100, "uptimeLast30m": 99.83235540653814, "uptimeLast1d": 98.96930781538973, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.85, "output": 14.25, "cacheRead": 0.285, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.35550158789464, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Amazon Bedrock", "tag": "amazon-bedrock/us-east-2", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 128000, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": null, "uptimeLast30m": 88.94080996884736, "uptimeLast1d": 93.19609284738998, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Chutes", "tag": "chutes/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 65535, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": null, "uptimeLast30m": 99.03100775193798, "uptimeLast1d": 97.22107863318237, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": 100, "uptimeLast30m": 90.04424778761062, "uptimeLast1d": 98.43904583928767, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Modal", "tag": "modal/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": 98.05825242718447, "uptimeLast30m": 95.1048951048951, "uptimeLast1d": 98.25454205126405, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Fireworks", "tag": "fireworks", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": null, "uptimeLast30m": 40.102827763496144, "uptimeLast1d": 99.31919768621117, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 98.01734820322181, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Moonshot AI", "tag": "moonshotai/mxfp4", "quantization": "mxfp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 3, "output": 15, "cacheRead": 0.3, "uptimeLast5m": 99.91735537190083, "uptimeLast30m": 99.98185611902386, "uptimeLast1d": 99.99442034484298, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Alibaba", "tag": "alibaba", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 3.45, "output": 17.25, "cacheRead": 0.345, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.19440322238711, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "InferenceNet", "tag": "inference-net/fast", "quantization": "fp4", "contextLength": 250000, "maxCompletionTokens": 225000, "input": 3.5, "output": 15, "cacheRead": 0.45, "uptimeLast5m": 100, "uptimeLast30m": 99.95928338762215, "uptimeLast1d": 99.80461896711219, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Fireworks", "tag": "fireworks/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 4.5, "output": 22.5, "cacheRead": 0.45, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 98.96946453142841, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Fireworks", "tag": "fireworks/fast", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 4.5, "output": 22.5, "cacheRead": 0.45, "uptimeLast5m": null, "uptimeLast30m": 97.37762237762237, "uptimeLast1d": 96.99048152295633, "latencyLast30mMs": null, "throughputLast30m": null } ] }, { "id": "z-ai/glm-5.3", "family": "GLM", "name": "Z.ai: GLM 5.3", "contextLength": 1048576, "openRouterListPrice": { "input": 0.07, "output": 7, "cacheRead": 0.065 }, "firstParty": null, "endpointsFetchStatus": 200, "endpoints": [ { "provider": "Relace", "tag": "relace", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 0.03, "output": 12, "cacheRead": 0.03, "uptimeLast5m": 99.89561586638831, "uptimeLast30m": 99.96233521657251, "uptimeLast1d": 99.96204542969078, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Wafer", "tag": "wafer/us", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.07, "output": 7, "cacheRead": 0.065, "uptimeLast5m": 99.967277486911, "uptimeLast30m": 99.80118270799348, "uptimeLast1d": 99.79741235138505, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "InferenceNet", "tag": "inference-net", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.14, "output": 4.4, "cacheRead": 0.07, "uptimeLast5m": 100, "uptimeLast30m": 99.74293059125964, "uptimeLast1d": 99.7237776307623, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Wafer", "tag": "wafer", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.15, "output": 7, "cacheRead": 0.14, "uptimeLast5m": 100, "uptimeLast30m": 99.75395430579965, "uptimeLast1d": 99.60004768432974, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Reka", "tag": "reka", "quantization": null, "contextLength": 262144, "maxCompletionTokens": 235929, "input": 0.17, "output": 3, "cacheRead": 0.169, "uptimeLast5m": 100, "uptimeLast30m": 99.8730964467005, "uptimeLast1d": 99.75644071621029, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Morph", "tag": "morph/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.179, "output": 3.553, "cacheRead": 0.137, "uptimeLast5m": 100, "uptimeLast30m": 99.82920580700257, "uptimeLast1d": 98.65589409850614, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Makora", "tag": "makora/fp4", "quantization": "fp4", "contextLength": 980000, "maxCompletionTokens": 128000, "input": 0.18, "output": 4.4, "cacheRead": 0.19, "uptimeLast5m": null, "uptimeLast30m": 93.8403041825095, "uptimeLast1d": 96.33566196227056, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AkashML", "tag": "akashml/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 0.19, "output": 4.4, "cacheRead": 0.19, "uptimeLast5m": 100, "uptimeLast30m": 99.66887417218543, "uptimeLast1d": 99.93010018972805, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Sail Research", "tag": "sail-research/us", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.2, "output": 3.4, "cacheRead": 0.15, "uptimeLast5m": 100, "uptimeLast30m": 99.3573264781491, "uptimeLast1d": 99.48462138584836, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Sail Research", "tag": "sail-research/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.2, "output": 3.4, "cacheRead": 0.15, "uptimeLast5m": 100, "uptimeLast30m": 99.76133651551312, "uptimeLast1d": 99.09330382103559, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Novita", "tag": "novita/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 0.42, "output": 1.32, "cacheRead": 0.078, "uptimeLast5m": 97.8978978978979, "uptimeLast30m": 98.14752441899628, "uptimeLast1d": 97.2327914216534, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DeepInfra", "tag": "deepinfra/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 0.5625, "output": 2.5, "cacheRead": 0.125, "uptimeLast5m": 95.65217391304348, "uptimeLast30m": 97.23502304147466, "uptimeLast1d": 97.24688898455256, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Inceptron", "tag": "inceptron/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.6, "output": 3.39, "cacheRead": 0.2, "uptimeLast5m": null, "uptimeLast30m": 95.23809523809523, "uptimeLast1d": 98.29399188446267, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "SiliconFlow", "tag": "siliconflow/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 0.7, "output": 2.2, "cacheRead": 0.13, "uptimeLast5m": 100, "uptimeLast30m": 99.886503357609, "uptimeLast1d": 99.84290591554026, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Phala", "tag": "phala", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.84, "output": 2.64, "cacheRead": 0.156, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.15990730011588, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "DigitalOcean", "tag": "digitalocean", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 128000, "input": 0.91, "output": 2.86, "cacheRead": 0.169, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.80182529335072, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "GMICloud", "tag": "gmicloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 0.98, "output": 3.08, "cacheRead": 0.182, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.74791318864776, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Alibaba", "tag": "alibaba", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 131072, "input": 1.19, "output": 3.74, "cacheRead": 0.238, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.94710114261532, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Decart", "tag": "decart/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.19, "output": 3.74, "cacheRead": 0.1955, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.9885898519899, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Friendli", "tag": "friendli", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.26, "output": 3.96, "cacheRead": 0.234, "uptimeLast5m": 100, "uptimeLast30m": 99.7564935064935, "uptimeLast1d": 99.94452589451996, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral/zdr", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.14, "uptimeLast5m": 100, "uptimeLast30m": 99.80551053484604, "uptimeLast1d": 99.72851823735675, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Baidu", "tag": "baidu/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.8858752397834, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 1.4, "output": 4.4, "cacheRead": 0.14, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 97.75286270947383, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral/nvfp4", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.14, "uptimeLast5m": 100, "uptimeLast30m": 99.93212669683258, "uptimeLast1d": 99.33962807088865, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Nebius", "tag": "nebius/fp4", "quantization": "fp4", "contextLength": 1024000, "maxCompletionTokens": 921600, "input": 1.4, "output": 4.4, "cacheRead": null, "uptimeLast5m": null, "uptimeLast30m": 77.2823779193206, "uptimeLast1d": 96.05476042314872, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Crusoe", "tag": "crusoe/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.91019308486754, "uptimeLast1d": 98.47936714142531, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "PrimeIntellect", "tag": "primeintellect", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.9804420105613, "uptimeLast1d": 99.47036170192926, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Venice", "tag": "venice", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.48805460750853, "uptimeLast1d": 98.63064568537344, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Together", "tag": "together", "quantization": null, "contextLength": 1048575, "maxCompletionTokens": 943717, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 99.31439764936337, "uptimeLast30m": 99.1138377641445, "uptimeLast1d": 96.37277958468852, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Parasail", "tag": "parasail/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.94145199063233, "uptimeLast1d": 99.7025275309785, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Modal", "tag": "modal", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.9215070643642, "uptimeLast1d": 98.12757807896287, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fp4", "quantization": "fp4", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 1.4, "output": 4.4, "cacheRead": 0.14, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 95.10014898195664, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Fireworks", "tag": "fireworks", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 99.55555555555556, "uptimeLast30m": 99.932478055368, "uptimeLast1d": 99.49602082110995, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Cloudflare", "tag": "cloudflare", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 98.1822903142041, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "AtlasCloud", "tag": "atlas-cloud/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.94321408290745, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Z.AI", "tag": "z-ai/fp8", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.4, "output": 4.4, "cacheRead": 0.26, "uptimeLast5m": 100, "uptimeLast30m": 99.95428571428572, "uptimeLast1d": 99.84018853456026, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Mistral", "tag": "mistral/nvfp4", "quantization": "nvfp4", "contextLength": 1048576, "maxCompletionTokens": 131072, "input": 1.54, "output": 4.84, "cacheRead": 0.154, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 99.81681931723564, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Fireworks", "tag": "fireworks/fast", "quantization": null, "contextLength": 1048576, "maxCompletionTokens": 943718, "input": 2.1, "output": 6.6, "cacheRead": 0.39, "uptimeLast5m": 100, "uptimeLast30m": 99.24085576259489, "uptimeLast1d": 99.59017044461741, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 2.1, "output": 6.6, "cacheRead": 0.21, "uptimeLast5m": 100, "uptimeLast30m": 100, "uptimeLast1d": 99.65149508608071, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "BaseTen", "tag": "baseten/fast", "quantization": "fp8", "contextLength": 1048576, "maxCompletionTokens": 262144, "input": 2.1, "output": 6.6, "cacheRead": 0.21, "uptimeLast5m": null, "uptimeLast30m": 100, "uptimeLast1d": 99.21168260532437, "latencyLast30mMs": null, "throughputLast30m": null }, { "provider": "Alibaba", "tag": "alibaba/fast", "quantization": null, "contextLength": 1000000, "maxCompletionTokens": 131072, "input": 2.8, "output": 8.8, "cacheRead": 0.56, "uptimeLast5m": null, "uptimeLast30m": null, "uptimeLast1d": 100, "latencyLast30mMs": null, "throughputLast30m": null } ] } ] }