{"uid":"cap_wO-ppPPSM_pPV9cqOtD-t","slug":"netintel-dev-chat-completions-gateway-e11af6c2","name":"netintel.dev Chat Completions Gateway","description":"OpenAI-compatible chat completions gateway — standard /v1/chat/completions path and request shape, model chosen in the body: any gpt-* chat model (not Claude/embeddings), each at its own price. Priced per model, $0.005–$0.65 per call in USDC via x402, no API key: POST unpaid and the 402 quotes your model's exact price. Supports response_format json_object. GET /v1/models (free) lists every model with its endpoint and price.","url":"https://netintel.dev/v1/chat/completions","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["model","messages"],"properties":{"model":{"type":"string","description":"Model id, e.g. gpt-4o-mini. Free catalog: GET /v1/models (every model, endpoint and price)"},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"type":"string","description":"system, user, or assistant"},"content":{"type":"string","description":"Message text"}}},"description":"OpenAI chat messages: [{role:'system'|'user'|'assistant', content:string}]"},"max_tokens":{"type":"number","description":"Max output tokens (clamped to the model's cap)."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"id":{"type":"string"},"model":{"type":"string"},"usage":{"type":"object"},"object":{"type":"string"},"choices":{"type":"array"}}}}}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-9f2f28d90a3c4e0f8f1c2d3e","model":"gpt-4o-mini","usage":{"total_tokens":15,"prompt_tokens":13,"completion_tokens":2},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"Hi!"},"finish_reason":"stop"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_uU1YUcoo-LUhQwAqm740e","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"OpenAI-compatible pay-per-call chat completions endpoint supporting GPT-4o, GPT-4.1, and other models — no OpenAI account needed, $0.10 USDC per call via x402","exampleAgentPrompt":"Ask gpt-4o to write me a concise executive summary of the following meeting transcript, keeping it under 200 words — use the standard chat completions endpoint and pay with USDC: [transcript text]","exampleUseCases":[{"title":"One-off LLM call without subscription","prompt":"I need to call gpt-4o to classify this support ticket as 'billing', 'technical', or 'general' — I don't have an OpenAI account, just pay the $0.10 per call with USDC. Ticket: 'My invoice this month looks wrong, I was charged twice.'"},{"title":"Agent pipeline LLM reasoning step","prompt":"Use gpt-4.1 to extract all action items from this project update email and return them as a JSON list — pay per call, no API key needed: 'Alice will finalize the spec by Friday, Bob needs to review the staging deploy, and Carol should send the client the revised proposal.'"},{"title":"Cheap nano-model summarization at scale","prompt":"Summarize this product review in one sentence using gpt-4o-mini — keep max_tokens at 60 to keep it short: 'This blender is incredibly powerful, handles ice and frozen fruit with ease, but the lid pops off occasionally at high speed which is a bit worrying.'"}],"resultDescription":"Returns a standard OpenAI chat completion object with a choices array containing the assistant's message, a model field, usage token counts (prompt_tokens, completion_tokens, total_tokens), and a unique completion ID — identical in shape to the OpenAI /v1/chat/completions response.","failureModes":["Payment not included or insufficient USDC — returns 402 Payment Required","Unsupported model ID — returns 400 with model not found error","Messages array missing required role or content fields — returns 400 validation error","max_tokens exceeds model cap — clamped silently or returns 400","Model capacity exceeded or upstream OpenAI timeout — returns 503 or 504","Malformed JSON body — returns 400 parse error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible chat completions without setting up an OpenAI account or managing API keys — especially useful in agent pipelines that pay per invocation using x402/USDC micropayments. Prefer it over the model-specific sibling endpoints (e.g. /v1/gpt-4.1) when you want a single flexible endpoint that selects the model via the request body. Avoid if you need streaming responses, function calling, or vision inputs not confirmed supported here.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:46:34.866Z","isFirstParty":false}