{"category":{"id":"model-inference","name":"Model APIs and inference","description":"LLM, embedding and multimodal model endpoints an agent can delegate sub-tasks to."},"entries":[
{"id":"anthropic-claude-api","name":"Anthropic Claude API","homepage":"https://docs.anthropic.com","docs":"https://platform.claude.com/docs/en/api/messages","auth":"api_key","auth_hint":"Authorization: Bearer <ANTHROPIC_API_KEY> (x-api-key still supported as legacy fallback), plus anthropic-version header","mcp":{"type":"none","url":null,"domain_verified":null,"kind":"none","config":null},"free_tier":"paid only","sdk":["python","typescript","java","go","csharp","php","ruby"],"openapi":null,"llms_txt":"https://platform.claude.com/docs/llms.txt","desc_en":"Send messages to Claude models for text and vision generation, tool use, batch jobs and document analysis.","notes":"docs.anthropic.com and docs.claude.com redirect to platform.claude.com. Rate limits depend on usage tier. The API's MCP connector lets Claude call remote MCP servers; there is no MCP server that wraps the API itself.","verified":"2026-09-24","auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <ANTHROPIC_API_KEY> + anthropic-version: 2023-06-01 (x-api-key still supported as legacy fallback)","source_url":"https://platform.claude.com/docs/en/api/overview","checked_at":"2026-09-24"},"base_url":"https://api.anthropic.com","rate_limits":{"summary":"Per usage tier and model (RPM, ITPM, OTPM); Start tier e.g. 1,000 RPM for Opus/Sonnet/Haiku; 429 on exceed","source_url":"https://platform.claude.com/docs/en/api/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Message Batches API: POST /v1/messages/batches, poll GET /v1/messages/batches/{id}, then fetch results","source_url":"https://platform.claude.com/docs/en/build-with-claude/batch-processing"},"data_policy":{"summary":"Retained data never used for training without express permission; prompts/outputs not retained by default except 30-day rule for Covered Models; ZDR available","source_url":"https://platform.claude.com/docs/en/manage-claude/api-and-data-retention","checked_at":"2026-09-24"},"operations":["llm-inference","image-understanding","document-parsing"],"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.anthropic.com","probes":1,"up":1,"median_ms":161,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"cohere-api","name":"Cohere API","homepage":"https://docs.cohere.com","docs":"https://docs.cohere.com/reference/about","auth":"api_key","auth_hint":"Authorization: Bearer <COHERE_API_KEY>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://docs.cohere.com/llms.txt","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"free trial key: 1,000 calls/mo, rate-limited","sdk":["python","typescript","java","go"],"openapi":null,"llms_txt":"https://docs.cohere.com/llms.txt","desc_en":"Call chat, embed, rerank and classify endpoints for text generation, semantic search and RAG.","notes":"Vendor MCP at https://docs.cohere.com/_mcp/server only searches the docs. Trial keys are not for production use. v2 API is current; v1 is legacy. Flagship chat model: command-a-plus-05-2026","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"1,000 API calls (trial/evaluation key)","period":"month","source_url":"https://docs.cohere.com/docs/rate-limits","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <COHERE_API_KEY>","source_url":"https://docs.cohere.com/v2/reference/chat","checked_at":"2026-09-24"},"base_url":"https://api.cohere.com/v2","rate_limits":{"summary":"Trial: Chat 20 req/min, Rerank 10/min, Embed 2,000 inputs/min; Production: Chat 500/min, Rerank 1,000/min","source_url":"https://docs.cohere.com/docs/rate-limits","checked_at":"2026-09-24"},"operations":["llm-inference","embeddings","reranking"],"no_auth":false,"call":{"operation":"chat / text generation","method":"POST","url":"https://api.cohere.com/v2/chat","example":"curl -X POST https://api.cohere.com/v2/chat -H \"Authorization: Bearer $COHERE_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"command-a-plus-05-2026\",\"messages\":[{\"role\":\"user\",\"content\":\"Tell me about LLMs\"}]}'","response_fields":["message.content[0].text","finish_reason","usage.billed_units","id"],"async":null,"source_url":"https://docs.cohere.com/v2/reference/chat","checked_at":"2026-09-24"},"unit_price":{"summary":"Command R: $0.15 input / $0.60 output per 1M tokens; Embed 4: $0.12 per 1M tokens; Rerank 4 Fast: $2 per 1K searches","source_url":"https://cohere.com/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","llms_txt":"ok"},"ratings":[{"source":"sourceforge","rating":4.0,"reviews":1,"url":"https://sourceforge.net/software/product/Cohere/","fetched_at":"2026-09-24T17:02Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.cohere.com/v2","probes":1,"up":1,"median_ms":270,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}},"mcp_remote":{"url":"https://docs.cohere.com/_mcp/server","probes":1,"up":1,"median_ms":289,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/cohere-api.json"},
{"id":"comet-opik","name":"Comet Opik Cloud API","homepage":"https://www.comet.com/site/products/opik/","docs":"https://www.comet.com/docs/opik/reference/rest-api/overview","auth":"api_key+oauth2","auth_hint":"Headers 'authorization: <OPIK_API_KEY>' (no Bearer prefix) and 'Comet-Workspace: <WORKSPACE>'; remote MCP uses browser sign-in","mcp":{"type":"official","url":"https://www.comet.com/opik/api/v1/mcp","maintainer":"vendor","remote_url":"https://www.comet.com/opik/api/v1/mcp","tools":["read","list","write","schema","read_skill"],"covers_full_api":false,"source_url":"https://www.comet.com/docs/opik/mcp-server/tools","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://www.comet.com/opik/api/v1/mcp","headers":null,"oauth":true,"docs_only":false,"source_url":"https://www.comet.com/docs/opik/mcp-server/advanced-setup","checked_at":"2026-09-24"}},"free_tier":"Free cloud plan: 25k spans/month, 60-day data retention, up to 10 team members","sdk":["python","javascript"],"openapi":null,"llms_txt":"https://www.comet.com/docs/opik/llms.txt","desc_en":"Lets an agent log and read LLM traces and spans, score them with evaluations and manage datasets and prompts in Opik.","notes":"REST base https://www.comet.com/opik/api/v1/private/. Remote MCP needs OAuth browser sign-in; local: uvx opik mcp configure.","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"25k spans, 60-day data retention, up to 10 team members","period":"month","source_url":"https://www.comet.com/site/pricing/","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"authorization","format":"authorization: <OPIK_API_KEY> (no Bearer prefix) + Comet-Workspace: <WORKSPACE>","source_url":"https://www.comet.com/docs/opik/reference/rest-api/overview","checked_at":"2026-09-24"},"base_url":"https://www.comet.com/opik/api/v1/private","data_policy":{"summary":"Free cloud plan keeps data 60 days","source_url":"https://www.comet.com/site/pricing/","checked_at":"2026-09-24"},"operations":["llm-observability"],"no_auth":false,"call":{"operation":"list traces of a project","method":"GET","url":"https://www.comet.com/opik/api/v1/private/traces?project_name={name}","example":"curl \"https://www.comet.com/opik/api/v1/private/traces?project_name=Default%20Project&size=10\" -H \"authorization: $OPIK_API_KEY\" -H \"Comet-Workspace: $OPIK_WORKSPACE\"","response_fields":["content[].id","content[].name","content[].input","content[].output","total"],"async":null,"source_url":"https://www.comet.com/docs/opik/reference/rest-api/traces/get-traces-by-project.md","checked_at":"2026-09-24"},"unit_price":{"summary":"Opik Cloud Pro: $19/mo incl. 100k spans, then $5 per extra 100k spans","source_url":"https://www.comet.com/site/pricing/","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"uptime":{"window_days":30,"api":{"url":"https://www.comet.com/opik/api/v1/private","probes":1,"up":1,"median_ms":422,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://www.comet.com/opik/api/v1/mcp","probes":1,"up":1,"median_ms":354,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}}},
{"id":"deepseek-api","name":"DeepSeek API","homepage":"https://api-docs.deepseek.com","docs":"https://api-docs.deepseek.com/api/deepseek-api","auth":"api_key","auth_hint":"Authorization: Bearer <DEEPSEEK_API_KEY>","mcp":{"type":"none","url":null,"domain_verified":null,"kind":"none","config":null},"free_tier":"paid only","sdk":[],"openapi":null,"llms_txt":null,"desc_en":"Send chat and reasoning requests to DeepSeek models via an OpenAI- and Anthropic-compatible REST API.","notes":"No native SDK: use the OpenAI SDK (base_url https://api.deepseek.com) or the Anthropic SDK (https://api.deepseek.com/anthropic). Off-peak is 50% off; peak is 01:00-04:00 and 06:00-10:00 UTC Mon-Fri. Fees come from a topped-up or granted balance.","verified":"2026-09-24","free_plan":{"kind":"none","source_url":"https://api-docs.deepseek.com/quick_start/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <DEEPSEEK_API_KEY>","source_url":"https://api-docs.deepseek.com/","checked_at":"2026-09-24"},"base_url":"https://api.deepseek.com","rate_limits":{"summary":"Account-level concurrency: deepseek-flash 2,500, deepseek-v4-pro 500 concurrent requests; 429 when exceeded","source_url":"https://api-docs.deepseek.com/quick_start/rate_limit","checked_at":"2026-09-24"},"operations":["llm-inference"],"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","llms_txt":"ok"},"ratings":[{"source":"sourceforge","rating":5.0,"reviews":1,"url":"https://sourceforge.net/software/product/DeepSeek/","fetched_at":"2026-09-24T17:02Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.deepseek.com","probes":1,"up":1,"median_ms":536,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/deepseek-api.json"},
{"id":"fal-ai","name":"fal.ai","homepage":"https://fal.ai","docs":"https://fal.ai/docs/model-apis","auth":"api_key+oauth2","auth_hint":"Authorization: Key <FAL_KEY>","mcp":{"type":"official","url":"https://mcp.fal.ai/mcp","maintainer":"vendor","remote_url":"https://mcp.fal.ai/mcp","tools":["search_models","get_model_schema","get_pricing","recommend_model","run_model","submit_job","check_job","get_job_result","cancel_job","upload_file","search_docs"],"covers_full_api":true,"source_url":"https://fal.ai/docs/documentation/setting-up/mcp","checked_at":"2026-09-24","domain_verified":false,"kind":"official","config":{"transport":"streamable-http","url":"https://mcp.fal.ai/mcp","headers":{"Authorization":"Bearer $FAL_KEY"},"oauth":true,"docs_only":false,"source_url":"https://fal.ai/docs/documentation/setting-up/mcp","checked_at":"2026-09-24"}},"free_tier":"Paid only; prepaid credits, priced per model (e.g. FLUX.1 schnell $0.003/megapixel)","sdk":["python","typescript"],"openapi":null,"llms_txt":"https://fal.ai/docs/llms.txt","desc_en":"Generate images, video, audio and 3D with 1,000+ hosted models via queued REST or real-time WebSocket.","notes":"REST auth header prefix is 'Key', not 'Bearer'; the MCP server takes 'Authorization: Bearer <FAL_KEY>' or OAuth. Long jobs use the queue API (submit, status, result).","verified":"2026-09-24","free_plan":{"kind":"none","source_url":"https://fal.ai/docs/documentation/model-apis/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"Authorization","format":"Authorization: Key <FAL_KEY>","source_url":"https://fal.ai/docs/documentation/model-apis/inference/queue","checked_at":"2026-09-24"},"base_url":"https://queue.fal.run","rate_limits":{"summary":"New accounts: 2 concurrent requests; limit rises with credit purchases (40+ via sales); excess requests wait in queue","source_url":"https://fal.ai/docs/documentation/model-apis/concurrency-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"POST https://queue.fal.run/{model} returns request_id, status_url, response_url; poll status or use webhooks","source_url":"https://fal.ai/docs/documentation/model-apis/inference/queue"},"data_policy":{"summary":"Request payloads stored 30 days by default (opt out with X-Fal-Store-IO: 0); generated media served as public CDN URLs","source_url":"https://fal.ai/docs/documentation/model-apis/media-expiration","checked_at":"2026-09-24"},"operations":["text-to-image","text-to-video","text-to-speech","text-to-3d"],"no_auth":false,"call":{"operation":"generate an image from a text prompt via the queue (FLUX.1 schnell)","method":"POST","url":"https://queue.fal.run/{model_id}","example":"curl -X POST https://queue.fal.run/fal-ai/flux/schnell -H \"Authorization: Key $FAL_KEY\" -H \"Content-Type: application/json\" -d '{\"prompt\": \"a sunset over mountains\"}'","response_fields":["request_id","status_url","response_url"],"async":"poll GET https://queue.fal.run/{model_id}/requests/{request_id}/status until COMPLETED, then GET .../requests/{request_id} (images[0].url)","source_url":"https://fal.ai/docs/documentation/model-apis/inference/queue","checked_at":"2026-09-24"},"unit_price":{"summary":"FLUX.1 [schnell]: $0.003 per megapixel (rounded up); price varies per model","source_url":"https://fal.ai/models/fal-ai/flux/schnell","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://queue.fal.run","probes":1,"up":1,"median_ms":209,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://mcp.fal.ai/mcp","probes":1,"up":1,"median_ms":183,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}}},
{"id":"fireworks-ai","name":"Fireworks AI","homepage":"https://fireworks.ai","docs":"https://docs.fireworks.ai","auth":"api_key","auth_hint":"Authorization: Bearer <FIREWORKS_API_KEY>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://docs.fireworks.ai/mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"trial credits: $1 on signup","sdk":["python"],"openapi":"https://docs.fireworks.ai/merged.openapi.yaml","llms_txt":"https://docs.fireworks.ai/llms.txt","desc_en":"Run serverless or dedicated inference and fine-tuning for open models via OpenAI-compatible APIs.","notes":"Vendor MCP at https://docs.fireworks.ai/mcp only searches the docs. The Responses API can call external MCP servers as tools.","verified":"2026-09-24","free_plan":{"kind":"trial","quota":"$1 in free credits","period":"one_time","source_url":"https://fireworks.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <FIREWORKS_API_KEY>","source_url":"https://docs.fireworks.ai/api-reference/post-chatcompletions","checked_at":"2026-09-24"},"base_url":"https://api.fireworks.ai/inference/v1","rate_limits":{"summary":"Adaptive serverless limits per account and model (TPM ceilings by model size); upper bound grows with spending tier; 429/503","source_url":"https://docs.fireworks.ai/serverless/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API: create batch job, it waits in pending state, poll job status","source_url":"https://docs.fireworks.ai/guides/batch-inference"},"data_policy":{"summary":"Does not log or store prompt or generation data for open models without explicit opt-in (zero data retention)","source_url":"https://docs.fireworks.ai/guides/security_compliance/data_security","checked_at":"2026-09-24"},"operations":["llm-inference","model-hosting"],"no_auth":false,"call":{"operation":"chat completion","method":"POST","url":"https://api.fireworks.ai/inference/v1/chat/completions","example":"curl https://api.fireworks.ai/inference/v1/chat/completions -H \"Content-Type: application/json\" -H \"Authorization: Bearer $FIREWORKS_API_KEY\" -d '{\"model\":\"accounts/fireworks/models/glm-5p3-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"Say hello in Spanish\"}]}'","response_fields":["choices[0].message.content","usage.prompt_tokens","usage.completion_tokens"],"async":null,"source_url":"https://docs.fireworks.ai/getting-started/quickstart","checked_at":"2026-09-24"},"unit_price":{"summary":"Serverless per 1M tokens, e.g. GLM 5.3 Flash $0.15 input / $0.50 output; unlisted models over 16B params $0.90 per 1M tokens","source_url":"https://docs.fireworks.ai/serverless/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","openapi":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.fireworks.ai/inference/v1","probes":1,"up":1,"median_ms":181,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://docs.fireworks.ai/mcp","probes":1,"up":1,"median_ms":404,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"google-gemini-api","name":"Google Gemini API","homepage":"https://ai.google.dev","docs":"https://ai.google.dev/api","auth":"api_key","auth_hint":"x-goog-api-key: <GEMINI_API_KEY> (or ?key= query param)","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://ai.google.dev/gemini-api/docs/coding-agents","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"free tier: rate-limited access to Flash/Pro models","sdk":["python","typescript","java","go"],"openapi":null,"llms_txt":"https://ai.google.dev/gemini-api/docs/llms.txt","desc_en":"Generate text and images, analyze multimodal input (video, audio, PDFs), and run code execution with Gemini models.","notes":"Vendor MCP at https://gemini-api-docs-mcp.dev only searches the docs. Free-tier content may be used to improve Google products. Unrestricted standard API keys are rejected in 2026; use a current key type. Google publishes a Discovery document, not OpenAPI. The quickstart now uses POST /v1beta/interactions (header Api-Revision: 2026-05-20) rather than generateContent","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"free input and output tokens on supported models, rate-limited per project","source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"x-goog-api-key","format":"x-goog-api-key: <GEMINI_API_KEY>","source_url":"https://ai.google.dev/gemini-api/docs/api-key","checked_at":"2026-09-24"},"base_url":"https://generativelanguage.googleapis.com/v1beta","rate_limits":{"summary":"Per project (not per key): RPM, TPM, RPD by model and tier (Free, Tier 1-3); view active limits in AI Studio","source_url":"https://ai.google.dev/gemini-api/docs/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API at 50% cost: create batch job, poll job state until JOB_STATE_SUCCEEDED","source_url":"https://ai.google.dev/gemini-api/docs/batch-api"},"data_policy":{"summary":"Free tier content used to improve Google products; paid tier content not used","source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked_at":"2026-09-24"},"operations":["llm-inference","text-to-image","image-understanding","code-execution","document-parsing"],"no_auth":false,"call":{"operation":"generate text","method":"POST","url":"https://generativelanguage.googleapis.com/v1beta/interactions","example":"curl -X POST https://generativelanguage.googleapis.com/v1beta/interactions -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"Content-Type: application/json\" -H \"Api-Revision: 2026-05-20\" -d '{\"model\": \"gemini-3.5-flash\", \"input\": \"Explain how AI works in a few words\"}'","response_fields":["id","status","steps[].content[0].text (step type model_output)","usage.total_tokens"],"async":null,"source_url":"https://ai.google.dev/gemini-api/docs/quickstart","checked_at":"2026-09-24"},"unit_price":{"summary":"gemini-3.5-flash paid tier: $1.50 per 1M input tokens, $9.00 per 1M output tokens (free tier available)","source_url":"https://ai.google.dev/gemini-api/docs/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://generativelanguage.googleapis.com/v1beta","probes":1,"up":1,"median_ms":131,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://gemini-api-docs-mcp.dev","probes":1,"up":1,"median_ms":388,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"groq-api","name":"Groq API","homepage":"https://console.groq.com","docs":"https://console.groq.com/docs/api-reference","auth":"api_key","auth_hint":"Authorization: Bearer <GROQ_API_KEY>","mcp":{"type":"none","url":null,"domain_verified":null,"kind":"none","config":null},"free_tier":"free tier: rate-limited per model, no card","sdk":["python","typescript"],"openapi":null,"llms_txt":"https://console.groq.com/llms.txt","desc_en":"Run fast LLM chat, tool use and speech-to-text on hosted open models via an OpenAI-compatible API.","notes":"Free-tier limits vary by model (e.g. 30 RPM / 1K RPD); see console.groq.com/settings/limits. Not to be confused with xAI Grok. Llama 3.x models (llama-3.3-70b-versatile, llama-3.1-8b-instant) are now contact-sales, not self-serve per-token","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"per-model limits, e.g. openai/gpt-oss-120b 30 RPM, 1K RPD, 8K TPM, 200K TPD","period":"day","source_url":"https://console.groq.com/docs/rate-limits","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <GROQ_API_KEY>","source_url":"https://console.groq.com/docs/api-reference","checked_at":"2026-09-24"},"base_url":"https://api.groq.com/openai/v1","rate_limits":{"summary":"Per model RPM/RPD/TPM/TPD; Free plan e.g. gpt-oss-120b 30 RPM, 1K RPD; Developer plan higher","source_url":"https://console.groq.com/docs/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API (Developer plan): POST /openai/v1/batches, poll GET /openai/v1/batches/{batch_id}","source_url":"https://console.groq.com/docs/batch"},"data_policy":{"summary":"Inference data not retained by default; retained up to 30 days only for batch/fine-tuning features or reliability needs","source_url":"https://console.groq.com/docs/your-data","checked_at":"2026-09-24"},"operations":["llm-inference","speech-to-text"],"no_auth":false,"call":{"operation":"chat completion","method":"POST","url":"https://api.groq.com/openai/v1/chat/completions","example":"curl https://api.groq.com/openai/v1/chat/completions -H \"Content-Type: application/json\" -H \"Authorization: Bearer $GROQ_API_KEY\" -d '{\"model\":\"openai/gpt-oss-120b\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain the importance of fast language models\"}]}'","response_fields":["choices[0].message.content","choices[0].finish_reason","usage.total_tokens","model"],"async":null,"source_url":"https://console.groq.com/docs/api-reference","checked_at":"2026-09-24"},"unit_price":{"summary":"openai/gpt-oss-120b: $0.15 per 1M input tokens, $0.60 per 1M output tokens (Llama 3.x models now listed as contact sales)","source_url":"https://console.groq.com/docs/models","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.groq.com/openai/v1","probes":1,"up":1,"median_ms":196,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"hugging-face-inference-providers","name":"Hugging Face Inference Providers","homepage":"https://huggingface.co/docs/inference-providers","docs":"https://huggingface.co/docs/inference-providers/index","auth":"api_key","auth_hint":"Authorization: Bearer <HF_TOKEN>","mcp":{"type":"official","url":"https://huggingface.co/mcp","maintainer":"vendor","remote_url":"https://huggingface.co/mcp","tools":["hf_whoami","hub_repo_search","hub_repo_details","hf_fs"],"covers_full_api":false,"source_url":"https://huggingface.co/mcp","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://huggingface.co/mcp","headers":{"Authorization":"Bearer $HF_TOKEN"},"oauth":true,"docs_only":false,"source_url":"https://github.com/huggingface/hf-mcp-server","checked_at":"2026-09-24"}},"free_tier":"Free tier: $0.10/month in Inference Providers credits (PRO $2.00/month)","sdk":["python","javascript"],"openapi":null,"llms_txt":"https://huggingface.co/docs/inference-providers/llms.txt","desc_en":"Call hundreds of open-weight chat, vision, image, video and audio models across many providers with one HF token.","notes":"The OpenAI-compatible endpoint (router.huggingface.co/v1) handles chat only; use InferenceClient for other tasks. The token needs the 'Make calls to Inference Providers' scope. Pick a provider with a model suffix such as :fastest or :cheapest.","verified":"2026-09-24","free_plan":{"kind":"free_tier","quota":"$0.10 in credits for free users (PRO $2.00)","period":"month","source_url":"https://huggingface.co/docs/inference-providers/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <HF_TOKEN>","source_url":"https://huggingface.co/docs/inference-providers/index","checked_at":"2026-09-24"},"base_url":"https://router.huggingface.co/v1","data_policy":{"summary":"HF does not store request/response bodies or use data for training; debug logs kept up to 30 days without user data","source_url":"https://huggingface.co/docs/inference-providers/security","checked_at":"2026-09-24"},"operations":["llm-inference","text-to-image","text-to-video","text-to-speech","image-understanding"],"no_auth":false,"call":{"operation":"chat completion on an open model","method":"POST","url":"https://router.huggingface.co/v1/chat/completions","example":"curl https://router.huggingface.co/v1/chat/completions -H \"Authorization: Bearer $HF_TOKEN\" -H 'Content-Type: application/json' -d '{\"model\":\"openai/gpt-oss-120b:fastest\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello!\"}],\"stream\":false}'","response_fields":["choices[0].message.content","usage"],"async":null,"source_url":"https://huggingface.co/docs/inference-providers/index","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://router.huggingface.co/v1","probes":1,"up":1,"median_ms":186,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://huggingface.co/mcp","probes":1,"up":1,"median_ms":202,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"mistral-ai-api","name":"Mistral AI API","homepage":"https://docs.mistral.ai","docs":"https://docs.mistral.ai/api","auth":"api_key","auth_hint":"Authorization: Bearer <MISTRAL_API_KEY>","mcp":{"type":"official","url":"https://api.mistral.ai/mcp","maintainer":"vendor","remote_url":"https://api.mistral.ai/mcp","covers_full_api":false,"source_url":"https://docs.mistral.ai/resources/mcp","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://api.mistral.ai/mcp","headers":{"Authorization":"Bearer $MISTRAL_API_KEY"},"oauth":false,"docs_only":false,"source_url":"https://docs.mistral.ai/resources/mcp","checked_at":"2026-09-24"}},"free_tier":"free tier: Studio free mode, rate-limited","sdk":["python","typescript"],"openapi":"https://docs.mistral.ai/openapi.yaml","llms_txt":"https://docs.mistral.ai/llms.txt","desc_en":"Run chat completions, embeddings, OCR and document processing with Mistral models via REST.","notes":"Official MCP (same API key) currently exposes only Studio Skills management tools, not chat inference; call the REST API for inference.","verified":"2026-09-24","free_plan":{"kind":"free_tier","requires_card":false,"quota":"included monthly usage within Free mode limits","period":"month","source_url":"https://docs.mistral.ai/getting-started/quickstarts/studio/activate-and-generate-api-key","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <MISTRAL_API_KEY>","source_url":"https://docs.mistral.ai/getting-started/quickstarts/studio/activate-and-generate-api-key","checked_at":"2026-09-24"},"base_url":"https://api.mistral.ai/v1","rate_limits":{"summary":"Per-model tokens-per-minute and other limits shown per organization in Admin Panel > API > Limits; Free mode has lower limits","source_url":"https://docs.mistral.ai/admin/billing-usage/usage-limits","checked_at":"2026-09-24"},"data_policy":{"summary":"Zero data retention available on paid plans for supported stateless API calls; training opt-out handled separately","source_url":"https://docs.mistral.ai/admin/monitor-comply/zero-data-retention","checked_at":"2026-09-24"},"operations":["llm-inference","ocr","embeddings","document-parsing"],"no_auth":false,"call":{"operation":"create a chat completion","method":"POST","url":"https://api.mistral.ai/v1/chat/completions","example":"curl https://api.mistral.ai/v1/chat/completions -H 'Content-Type: application/json' -H \"Authorization: Bearer $MISTRAL_API_KEY\" -d '{\"model\": \"mistral-large-latest\", \"messages\": [{\"role\": \"user\", \"content\": \"Who is the best French painter? Answer in one short sentence.\"}]}'","response_fields":["choices[0].message.content","choices[0].finish_reason","usage.total_tokens"],"async":null,"source_url":"https://docs.mistral.ai/api/","checked_at":"2026-09-24"},"unit_price":{"summary":"Mistral Large: $0.5 per 1M input tokens, $1.5 per 1M output tokens; Batch API 50% off","source_url":"https://mistral.ai/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":true,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"sourceforge","rating":5.0,"reviews":1,"url":"https://sourceforge.net/software/product/Mistral-AI/","fetched_at":"2026-09-24T17:02Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.mistral.ai/v1","probes":1,"up":1,"median_ms":268,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://api.mistral.ai/mcp","probes":1,"up":1,"median_ms":268,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/mistral-ai-api.json"},
{"id":"openai-api","name":"OpenAI API","homepage":"https://platform.openai.com","docs":"https://developers.openai.com/api/reference/overview","auth":"api_key","auth_hint":"Authorization: Bearer <OPENAI_API_KEY>","mcp":{"type":"official","url":"https://developers.openai.com/mcp","maintainer":"vendor","remote_url":"https://developers.openai.com/mcp","tools":["search_openai_docs","list_openai_docs","fetch_openai_doc","list_api_endpoints","get_openapi_spec"],"covers_full_api":false,"source_url":"https://developers.openai.com/learn/docs-mcp","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://developers.openai.com/mcp","derived":true}},"free_tier":"paid only","sdk":["python","typescript","csharp","java","go","ruby"],"openapi":"https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml","llms_txt":"https://developers.openai.com/llms.txt","desc_en":"Generate text, images, audio and embeddings, and run tool-calling via the Responses and Chat Completions APIs.","notes":"Docs moved from platform.openai.com to developers.openai.com (old URLs redirect). Usage-based billing with a payment method; rate limits scale with usage tier. The official MCP server is documentation-only and does not call the API.","verified":"2026-09-24","operations":["llm-inference","text-to-image","text-to-speech","speech-to-text","embeddings"],"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <OPENAI_API_KEY>","source_url":"https://developers.openai.com/api/reference/overview","checked_at":"2026-09-24"},"base_url":"https://api.openai.com/v1","rate_limits":{"summary":"RPM/RPD/TPM/TPD/IPM per model, set by usage tier (Free, Tier 1-5); 429 slow_down / rate_limit_error","source_url":"https://developers.openai.com/api/docs/guides/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API: upload JSONL, create batch, poll batch status (completes within 24h)","source_url":"https://developers.openai.com/api/docs/guides/batch"},"data_policy":{"summary":"API data not used for training unless you opt in; abuse-monitoring logs kept 30 days; ZDR available for approved customers","source_url":"https://developers.openai.com/api/docs/guides/your-data","checked_at":"2026-09-24"},"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"sourceforge","rating":5.0,"reviews":3,"url":"https://sourceforge.net/software/product/OpenAI/","fetched_at":"2026-09-24T17:02Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.openai.com/v1","probes":1,"up":1,"median_ms":252,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://developers.openai.com/mcp","probes":1,"up":1,"median_ms":266,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/openai-api.json"},
{"id":"openrouter","name":"OpenRouter","homepage":"https://openrouter.ai","docs":"https://openrouter.ai/docs/api-reference/overview","auth":"api_key+oauth2","auth_hint":"Authorization: Bearer <OPENROUTER_API_KEY>","mcp":{"type":"official","url":"https://mcp.openrouter.ai/mcp","maintainer":"vendor","remote_url":"https://mcp.openrouter.ai/mcp","tools":["send-message","generate-image","list-models","get-model","list-model-endpoints","list-providers","list-daily-model-rankings","list-app-rankings","get-credits","get-generation","list-benchmarks","list-task-classifications","search-docs","send-feedback","spawn-ori-eval","install-ori-harness","ping"],"covers_full_api":false,"source_url":"https://openrouter.ai/docs/guides/overview/mcp-server","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"streamable-http","url":"https://mcp.openrouter.ai/mcp","headers":null,"oauth":true,"docs_only":false,"source_url":"https://openrouter.ai/docs/guides/overview/mcp-server","checked_at":"2026-09-24"}},"free_tier":"free models: 50 req/day (1,000/day after $10 purchase)","sdk":["typescript","python"],"openapi":"https://openrouter.ai/openapi.json","llms_txt":"https://openrouter.ai/docs/llms.txt","desc_en":"Route chat requests to hundreds of LLMs from many providers through one OpenAI-compatible endpoint with fallback.","notes":"The official remote MCP server uses OAuth PKCE and mints a 7-day key with a $10 default spend limit. It includes send-message and generate-image tools. OAuth PKCE is also available for apps.","verified":"2026-09-24","operations":["llm-inference","text-to-image"],"free_plan":{"kind":"free_tier","requires_card":false,"quota":"free models: 50 requests/day (1,000/day once $10+ credits purchased), 20 RPM","period":"day","source_url":"https://openrouter.ai/docs/api_reference/limits","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <OPENROUTER_API_KEY>","source_url":"https://openrouter.ai/docs/api-reference/overview","checked_at":"2026-09-24"},"base_url":"https://openrouter.ai/api/v1","rate_limits":{"summary":"Free models 20 RPM and 50 RPD (1,000 RPD with >= $10 credits); paid models limited by provider/DDoS protection; X-RateLimit-* headers","source_url":"https://openrouter.ai/docs/api_reference/limits","checked_at":"2026-09-24"},"data_policy":{"summary":"OpenRouter does not store prompts or responses unless you opt in; provider training/logging policies documented per provider","source_url":"https://openrouter.ai/docs/guides/privacy/data-collection","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"send a chat completion to a routed model","method":"POST","url":"https://openrouter.ai/api/v1/chat/completions","example":"curl https://openrouter.ai/api/v1/chat/completions -H \"Content-Type: application/json\" -H \"Authorization: Bearer $OPENROUTER_API_KEY\" -d '{\"model\":\"~openai/gpt-sol-latest\",\"messages\":[{\"role\":\"user\",\"content\":\"What is the meaning of life?\"}]}'","response_fields":["id","model","choices[0].message.content","usage"],"async":null,"source_url":"https://openrouter.ai/docs/quickstart","checked_at":"2026-09-24"},"unit_price":{"summary":"Tokens billed at the provider's list price per model (no markup); 5.5% fee on credit purchases (Standard), 8% (Business)","source_url":"https://openrouter.ai/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":true,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","openapi":"ok","llms_txt":"ok"},"ratings":[{"source":"sourceforge","rating":5.0,"reviews":1,"url":"https://sourceforge.net/software/product/OpenRouter/","fetched_at":"2026-09-24T17:02Z"}],"uptime":{"window_days":30,"api":{"url":"https://openrouter.ai/api/v1","probes":1,"up":1,"median_ms":336,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://mcp.openrouter.ai/mcp","probes":1,"up":1,"median_ms":183,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}},"reviews_url":"https://raw.githubusercontent.com/eater2/ai_agents_api_library/main/catalog/reviews/openrouter.json"},
{"id":"piapi","name":"PiAPI","homepage":"https://piapi.ai","docs":"https://piapi.ai/docs/overview","auth":"api_key","auth_hint":"X-API-Key: <key>","mcp":{"type":"community","url":"https://github.com/apinetwork/piapi-mcp-server","maintainer":"community","repo":"https://github.com/apinetwork/piapi-mcp-server","covers_full_api":true,"source_url":"https://github.com/apinetwork/piapi-mcp-server","checked_at":"2026-09-24","domain_verified":null,"kind":"community","config":{"transport":"stdio","command":"node","args":["/path/to/piapi-mcp-server/dist/index.js"],"env":["PIAPI_API_KEY"],"docs_only":false,"source_url":"https://github.com/apinetwork/piapi-mcp-server#connecting-to-claude-desktop","checked_at":"2026-09-24"}},"free_tier":"trial credits: $0.50 on signup","sdk":[],"openapi":null,"llms_txt":"https://piapi.ai/llms.txt","desc_en":"Generate images, video and music through one API proxying Midjourney, Flux, Kling and other models.","notes":"Third-party reseller, not the model owner. The Midjourney access is unofficial, so it can break or violate Midjourney's terms of service. Tasks are async (create task, then poll or webhook).","verified":"2026-09-24","operations":["text-to-image","text-to-video","music-generation"],"free_plan":{"kind":"trial","quota":"$0.50 in free credits","period":"one_time","source_url":"https://piapi.ai/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"apiKey","in":"header","name":"X-API-Key","format":"X-API-Key: <PIAPI_KEY>","source_url":"https://piapi.ai/docs/quickstart","checked_at":"2026-09-24"},"base_url":"https://api.piapi.ai","async_jobs":{"value":true,"how":"POST https://api.piapi.ai/api/v1/task creates a task; get task endpoint for results, or webhook notifications","source_url":"https://piapi.ai/docs/overview"},"no_auth":false,"call":{"operation":"generate an image from text (Flux)","method":"POST","url":"https://api.piapi.ai/api/v1/task","example":"curl -X POST https://api.piapi.ai/api/v1/task -H \"X-API-Key: $PIAPI_KEY\" -H \"Content-Type: application/json\" -d '{\"model\":\"Qubico/flux1-schnell\",\"task_type\":\"txt2img\",\"input\":{\"prompt\":\"a little cat\",\"width\":1024,\"height\":1024}}'","response_fields":["data.task_id","data.status","data.output.image_url"],"async":"poll GET https://api.piapi.ai/api/v1/task/{task_id} until data.status is completed","source_url":"https://piapi.ai/docs/flux-api/text-to-image","checked_at":"2026-09-24"},"unit_price":{"summary":"Flux: flux1-schnell $0.0015 per image, flux1-dev $0.015 per image, flux1-dev-advanced $0.02 per image","source_url":"https://piapi.ai/flux-api/llms.txt","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":true,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","llms_txt":"ok"},"ratings":[{"source":"github","repo":"apinetwork/piapi-mcp-server","stars":75,"forks":22,"pushed_at":"2026-09-17","archived":false,"url":"https://github.com/apinetwork/piapi-mcp-server","fetched_at":"2026-09-24T16:54Z"}],"uptime":{"window_days":30,"api":{"url":"https://api.piapi.ai","probes":1,"up":1,"median_ms":435,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"replicate","name":"Replicate","homepage":"https://replicate.com","docs":"https://replicate.com/docs/reference/http","auth":"api_key","auth_hint":"Authorization: Bearer <REPLICATE_API_TOKEN>","mcp":{"type":"official","url":"https://mcp.replicate.com/sse","maintainer":"vendor","remote_url":"https://mcp.replicate.com/sse","repo":"https://www.npmjs.com/package/replicate-mcp","source_url":"https://replicate.com/docs/reference/mcp","checked_at":"2026-09-24","domain_verified":true,"kind":"vendor-hosted","config":{"transport":"sse","url":"https://mcp.replicate.com/sse","headers":null,"oauth":true,"docs_only":false,"source_url":"https://mcp.replicate.com","checked_at":"2026-09-24"}},"free_tier":"paid only","sdk":["python","javascript","swift","go"],"openapi":"https://api.replicate.com/openapi.json","llms_txt":"https://replicate.com/llms.txt","desc_en":"Run thousands of hosted image, video, audio and text models via HTTP predictions; also fine-tune and deploy.","notes":"Billed per second of compute or per output. The MCP server is also available locally via npx replicate-mcp.","verified":"2026-09-24","operations":["text-to-image","text-to-video","text-to-speech","llm-inference","model-hosting"],"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <REPLICATE_API_TOKEN>","source_url":"https://replicate.com/docs/reference/http","checked_at":"2026-09-24"},"base_url":"https://api.replicate.com/v1","rate_limits":{"summary":"Create prediction 600 req/min; other endpoints 3,000 req/min; accounts with granted credit but no payment method: 6 req/min","source_url":"https://replicate.com/docs/topics/predictions/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"POST /v1/predictions returns a prediction to poll (GET /v1/predictions/{id}) or use webhooks; 'Prefer: wait' blocks up to 60s","source_url":"https://replicate.com/docs/reference/http"},"data_policy":{"summary":"API prediction inputs, outputs, files and logs deleted automatically after one hour by default","source_url":"https://replicate.com/docs/topics/predictions/data-retention","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"run an official model and wait for the output (FLUX schnell text-to-image)","method":"POST","url":"https://api.replicate.com/v1/models/{owner}/{name}/predictions","example":"curl -s -X POST https://api.replicate.com/v1/models/black-forest-labs/flux-schnell/predictions -H \"Authorization: Bearer $REPLICATE_API_TOKEN\" -H 'Content-Type: application/json' -H 'Prefer: wait' -d '{\"input\": {\"prompt\": \"a sunset over mountains\"}}'","response_fields":["id","status","output","error","urls.get"],"async":"if status is not succeeded after the 60 s wait, poll GET https://api.replicate.com/v1/predictions/{id}","source_url":"https://replicate.com/docs/reference/http","checked_at":"2026-09-24"},"unit_price":{"summary":"black-forest-labs/flux-schnell: $3.00 per 1,000 output images ($0.003/image); other models billed per output or per second of compute","source_url":"https://replicate.com/pricing","checked_at":"2026-09-24"},"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","openapi":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.replicate.com/v1","probes":1,"up":1,"median_ms":259,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}},"mcp_remote":{"url":"https://mcp.replicate.com/sse","probes":1,"up":1,"median_ms":279,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}}},
{"id":"together-ai","name":"Together AI","homepage":"https://www.together.ai","docs":"https://docs.together.ai","auth":"api_key","auth_hint":"Authorization: Bearer <TOGETHER_API_KEY>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://docs.together.ai/docs/agent-skills.md","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"Paid only: no free trial; minimum $5 prepaid credit purchase","sdk":["python","typescript"],"openapi":"https://docs.together.ai/openapi.yaml","llms_txt":"https://docs.together.ai/llms.txt","desc_en":"Run serverless inference, batch jobs, fine-tuning and dedicated GPU endpoints for open-source models.","notes":"Vendor MCP at https://docs.together.ai/mcp only searches the docs. The API is OpenAI-compatible.","verified":"2026-09-24","operations":["llm-inference","model-hosting"],"free_plan":{"kind":"none","source_url":"https://docs.together.ai/docs/billing-credits","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <TOGETHER_API_KEY>","source_url":"https://docs.together.ai/docs/api-keys-authentication","checked_at":"2026-09-24"},"base_url":"https://api.together.ai/v1","rate_limits":{"summary":"Dynamic per-model limits that scale with sustained traffic; 429 includes x-ratelimit-reset","source_url":"https://docs.together.ai/docs/serverless/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API: upload JSONL, start batch job, poll until finished, retrieve results (up to 50% cheaper)","source_url":"https://docs.together.ai/docs/inference/batch/tutorial"},"data_policy":{"summary":"By default stores prompts/responses and may use them for product improvement (admins can disable); training on org data is opt-in","source_url":"https://docs.together.ai/docs/privacy-and-security","checked_at":"2026-09-24"},"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"ok","openapi":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.together.ai/v1","probes":1,"up":1,"median_ms":453,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://docs.together.ai/mcp","probes":1,"up":1,"median_ms":591,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}},
{"id":"vercel-ai-gateway","name":"Vercel AI Gateway","homepage":"https://vercel.com/ai-gateway","docs":"https://vercel.com/docs/ai-gateway/sdks-and-apis","auth":"api_key+oauth2","auth_hint":"Authorization: Bearer <AI_GATEWAY_API_KEY>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://vercel.com/docs/agent-resources/vercel-mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"free tier: monthly credits on subset of models","sdk":["typescript","python"],"openapi":null,"llms_txt":"https://vercel.com/llms.txt","desc_en":"Send chat, image, embedding and rerank requests to 100+ models through one gateway with failover and spend tracking.","notes":"The base URL https://ai-gateway.vercel.sh works with OpenAI and Anthropic SDKs. Vercel's platform MCP (mcp.vercel.com) does not call the gateway, only buys its credits. Tokens have no markup. BYOK requires the paid tier. Free-tier overage returns 429. On Vercel, OIDC tokens can replace the API key.","verified":"2026-09-24","operations":["llm-inference","text-to-image","embeddings","reranking"],"free_plan":{"kind":"free_tier","quota":"free AI Gateway credits on a subset of models, rate-limited per model","source_url":"https://vercel.com/docs/ai-gateway/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <AI_GATEWAY_API_KEY> (or Vercel OIDC token)","source_url":"https://vercel.com/docs/ai-gateway/sdks-and-apis","checked_at":"2026-09-24"},"base_url":"https://ai-gateway.vercel.sh/v1","rate_limits":{"summary":"Free tier: lower per-model limits (429); paid tier: no AI Gateway limits, only upstream provider limits","source_url":"https://vercel.com/docs/ai-gateway/rate-limits","checked_at":"2026-09-24"},"data_policy":{"summary":"Per-request Zero Data Retention routing to providers that do not retain or train on prompts (Pro and Enterprise)","source_url":"https://vercel.com/docs/ai-gateway/pricing","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"create a chat completion","method":"POST","url":"https://ai-gateway.vercel.sh/v1/chat/completions","example":"curl -X POST https://ai-gateway.vercel.sh/v1/chat/completions -H \"Authorization: Bearer $AI_GATEWAY_API_KEY\" -H \"Content-Type: application/json\" -d '{\"model\": \"anthropic/claude-opus-5\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]}'","response_fields":["choices[0].message.content","choices[0].finish_reason","usage.total_tokens","model"],"source_url":"https://vercel.com/docs/ai-gateway/sdks-and-apis/openai-chat-completions/chat-completions","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://ai-gateway.vercel.sh/v1","probes":1,"up":1,"median_ms":447,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://mcp.vercel.com","probes":1,"up":1,"median_ms":238,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":401}}}},
{"id":"voyage-ai-embeddings-rerank","name":"Voyage AI (embeddings/rerank)","homepage":"https://www.voyageai.com","docs":"https://docs.voyageai.com/reference/embeddings-api","auth":"api_key","auth_hint":"Authorization: Bearer <VOYAGE_API_KEY>","mcp":{"type":"none","url":null,"domain_verified":null,"kind":"none","config":null},"free_tier":"free tier: 200M tokens on current models","sdk":["python"],"openapi":null,"llms_txt":"https://docs.voyageai.com/llms.txt","desc_en":"Generate text, code and multimodal embeddings and rerank documents for RAG and semantic search.","notes":"Owned by MongoDB, but the standalone API at api.voyageai.com is still self-serve. Free tokens do not apply to the Batch API.","verified":"2026-09-24","operations":["embeddings","reranking"],"free_plan":{"kind":"free_tier","quota":"first 200 million tokens per account on current models (e.g. voyage-4, voyage-4-large)","period":"one_time","source_url":"https://docs.voyageai.com/docs/pricing","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <VOYAGE_API_KEY>","source_url":"https://docs.voyageai.com/reference/embeddings-api","checked_at":"2026-09-24"},"base_url":"https://api.voyageai.com/v1","rate_limits":{"summary":"Per model RPM/TPM by usage tier (Tier 1 = payment method added), e.g. voyage-3.5 2,000 RPM / 8M TPM; Tier 2 2x, Tier 3 3x","source_url":"https://docs.voyageai.com/docs/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API: upload .jsonl file, create batch, poll GET retrieve batch","source_url":"https://docs.voyageai.com/docs/batch-inference"},"data_policy":{"summary":"Voyage may store and use API data for training unless an org admin with a payment method opts out (then zero-day retention)","source_url":"https://docs.voyageai.com/docs/faq","checked_at":"2026-09-24"},"no_auth":false,"call":{"operation":"embed texts","method":"POST","url":"https://api.voyageai.com/v1/embeddings","example":"curl -X POST https://api.voyageai.com/v1/embeddings -H \"Authorization: Bearer $VOYAGE_API_KEY\" -H \"content-type: application/json\" -d '{\"input\":[\"Sample text 1\",\"Sample text 2\"],\"model\":\"voyage-4\"}'","response_fields":["data[].embedding","data[].index","model","usage.total_tokens"],"async":null,"source_url":"https://docs.voyageai.com/reference/embeddings-api","checked_at":"2026-09-24"},"unit_price":{"summary":"voyage-4: $0.06 per 1M tokens (voyage-4-lite $0.02, voyage-4-large $0.12); first 200M tokens free","source_url":"https://docs.voyageai.com/docs/pricing","checked_at":"2026-09-24"},"has_free_tier":true,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.voyageai.com/v1","probes":1,"up":1,"median_ms":212,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}}}},
{"id":"xai-grok-api","name":"xAI Grok API","homepage":"https://docs.x.ai","docs":"https://docs.x.ai/developers/rest-api-reference/inference","auth":"api_key","auth_hint":"Authorization: Bearer <XAI_API_KEY>","mcp":{"type":"none","url":null,"maintainer":"none","source_url":"https://docs.x.ai/developers/docs-mcp","checked_at":"2026-09-24","domain_verified":null,"kind":"none","config":null},"free_tier":"paid only (prepaid credits)","sdk":["python"],"openapi":"https://docs.x.ai/openapi.json","llms_txt":"https://docs.x.ai/llms.txt","desc_en":"Generate text, images, video and voice with Grok models, with built-in web search and code tools.","notes":"The account must have prepaid credits (console.x.ai). The API is OpenAI-compatible (/v1/responses, /v1/chat/completions). Vendor MCP at https://docs.x.ai/api/mcp only searches the docs.","verified":"2026-09-24","operations":["llm-inference","text-to-image","text-to-video","text-to-speech","web-search"],"free_plan":{"kind":"none","source_url":"https://docs.x.ai/developers/quickstart","checked_at":"2026-09-24"},"auth_scheme":{"type":"http","scheme":"bearer","format":"Authorization: Bearer <XAI_API_KEY>","source_url":"https://docs.x.ai/developers/quickstart","checked_at":"2026-09-24"},"base_url":"https://api.x.ai/v1","rate_limits":{"summary":"Per-model RPS (RPM/60) and TPM by tier; tier based on cumulative spend since 2026-01-01 (Tier 0 $0, Tier 1 $50, Tier 2 $250...)","source_url":"https://docs.x.ai/developers/rate-limits","checked_at":"2026-09-24"},"async_jobs":{"value":true,"how":"Batch API: create batch, add requests, poll batch status until num_pending is 0","source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api"},"no_auth":false,"has_free_tier":false,"has_trial":false,"no_card":false,"stale":false,"link_check":{"checked_at":"2026-09-24","docs":"ok","mcp":"reachable","openapi":"ok","llms_txt":"ok"},"uptime":{"window_days":30,"api":{"url":"https://api.x.ai/v1","probes":1,"up":1,"median_ms":259,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":404}},"mcp_remote":{"url":"https://docs.x.ai/api/mcp","probes":1,"up":1,"median_ms":224,"last":{"at":"2026-09-24T18:26Z","up":true,"detail":200}}}}
]}