{"uid":"cap_2BWvmySG3sh909O0bbuBs","slug":"farout-llm-gateway-38ecd2c4","name":"FarOut LLM Gateway","description":"[OI]-compatible LLM inference API for autonomous agents. Supports reasoning, coding and chat workloads. Pay with USDC on Base using x402 (upto scheme, true-up billing): the 402 quotes a spending CAP (estimated input tokens + your max_tokens at the model's per-1M price), and after the model answers you are settled for the ACTUAL usage — always <= the cap, never more. Minimum $0.001, cap $3.0 per call. Cached input bills at 10%. Failed calls are never charged. Any model from GET /v1/models.","url":"https://farouter.tech/v1/messages","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"Model id from GET /v1/models, e.g. glm-5.3. No provider prefix."},"stream":{"type":"boolean","description":"SSE streaming."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","developer","user","assistant","tool"],"type":"string"},"content":{}},"additionalProperties":true},"minItems":1,"description":"Chat messages, [OI]-compatible {role, content}."},"max_tokens":{"type":"integer","minimum":1,"description":"Output token budget. Sets your spending cap; actual usage is what gets settled (true-up)."},"temperature":{"type":"number","maximum":2,"minimum":0,"description":"Sampling temperature."},"max_completion_tokens":{"type":"integer","minimum":1,"description":"Alias of max_tokens (gpt-5.x models)."}}},"responseSchema":{"type":"json","example":{"usage":{"prompt_tokens":6,"completion_tokens":8},"choices":[{"message":{"role":"assistant","content":"Hello! How can I help?"},"finish_reason":"stop"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_OHADWp6KqwcBNNbQUk5Ee","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Pay-per-call LLM inference endpoint supporting OpenAI-compatible chat/reasoning/coding across 17 frontier models, billed per request in USDC on Base via x402","exampleAgentPrompt":"Using FarOut, send the user message 'Explain quantum entanglement in two sentences' to glm-5.3 with a max of 200 output tokens and get the response.","exampleUseCases":[{"title":"Autonomous agent reasoning task","prompt":"I need you to use the FarOut gateway to ask DeepSeek V4 to reason through this logic puzzle step by step: 'If all A are B, and some B are C, what can we conclude about A and C?' — give it a budget of 512 tokens."},{"title":"On-demand code generation","prompt":"Hit the FarOut LLM API with model glm-5.3 and ask it to write a Python function that parses a JWT token without a library — cap it at 300 tokens."},{"title":"Crypto-native chatbot response","prompt":"My agent needs to reply to a user question using Gemini 3.1 via FarOut — the user asked 'What are the tax implications of staking ETH?' — use temperature 0.2 and a 400-token limit."}],"resultDescription":"Returns an OpenAI-compatible JSON object with a choices array containing the assistant's message and finish_reason, plus a usage object showing prompt_tokens and completion_tokens consumed.","failureModes":["Payment failure or insufficient USDC balance on Base — returns 402 Payment Required","Invalid or unrecognized model ID — returns 400 with model not found error","max_tokens too low for the requested workload — truncated or empty completion","messages array empty or malformed — returns 400 validation error","Model temporarily unavailable — returns 503 or upstream timeout","Streaming connection dropped mid-response — partial SSE stream"],"whenToPreferThis":"Choose this endpoint when an autonomous agent needs keyless, accountless LLM inference paid per-call in USDC on Base via x402 — ideal for AI agents that must avoid subscription management, need access to a broad roster of frontier models (GPT-5.6, DeepSeek V4, Gemini 3.1, Kimi K3, GLM 5.3, MiniMax M3) through a single OpenAI-compatible interface, and require crypto-native micropayment billing with no prepaid balance.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:40:24.949Z","isFirstParty":false}