{"uid":"cap_9uwPTpAHf_q8LBEfAkYC_","slug":"taifoon-gpt-oss-20b-chat-completion-6d04ce3d","name":"Taifoon: GPT-OSS-20B Chat Completion","description":"OpenAI-compatible chat completion on openai/gpt-oss-20b, served by DeepInfra (serverless inference) and sold by Taifoon at the provider's price plus a 20 % reseller cut: 0.036 / 0.168 USD per 1M tokens in/out. This request is priced at its prompt and max_tokens. The answer is checked before you are charged.","url":"https://coord.taifoon.dev/v1/chat/completions/gpt-oss-20b?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","examples":["l3-8b-lunaris-v1","llama-3.1-8b-instruct","mistral-small-24b-instruct-2501","gemma-3-4b-it","gpt-oss-20b","phi-4","qwen2.5-7b-instruct","gemma-3-12b-it","qwen3.5-9b","gemma-3-27b-it","ling-3.0-flash","ling-3.0-flash-vl"],"description":"optional; one of the 76 models this wall delivers (GET lists them under terms.models); without it nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 answers"},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"maxItems":32,"minItems":1},"max_tokens":{"type":"integer","maximum":700,"minimum":1}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-gpu_…","model":"nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16","usage":{"total_tokens":28,"prompt_tokens":14,"completion_tokens":14},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"17 × 24 = 408 (17 × 20 = 340; 17 × 4 = 68; 340 + 68 = 408)."},"finish_reason":"stop"}],"created":1791763200}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001512","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":"$0.0012/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0012","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0012","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_vyE9oNnwvXrJUfKZ00kmF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0012","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"OpenAI-compatible chat completion endpoint serving the gpt-oss-20b model (and 70+ others) via Taifoon's coordination layer, billed per call via x402.","exampleAgentPrompt":"Ask the gpt-oss-20b model via Taifoon: given the messages 'system: you are a helpful assistant' and 'user: explain quantum entanglement in two sentences', give me a response with at most 300 tokens.","exampleUseCases":[{"title":"Quick reasoning task on demand","prompt":"Use the gpt-oss-20b model to answer this math question in under 200 tokens: what is 17 multiplied by 24, and show the working?"},{"title":"Lightweight chatbot for automated pipeline","prompt":"Send this conversation to the gpt-oss-20b model — system: you are a customer support agent; user: my order hasn't arrived in 10 days — and get a helpful reply, max 400 tokens."},{"title":"Content generation with model selection","prompt":"Generate a 3-sentence product description for noise-cancelling headphones using the qwen2.5-7b-instruct model through Taifoon, keeping it under 300 tokens."}],"resultDescription":"A JSON chat completion object in OpenAI format containing: a unique completion ID, the model used, token usage breakdown (prompt, completion, total), and a choices array with the assistant's message content and finish reason (e.g. 'stop').","failureModes":["Invalid or missing messages array returns 400","max_tokens exceeds 700 returns validation error","Model name not in supported list may fall back to default or error","Missing x402 payment header returns 402 Payment Required","Rate limit or quota exceeded returns 429","Upstream GPU inference timeout returns 5xx"],"whenToPreferThis":"Choose this endpoint when you need pay-per-call LLM inference with no subscription, billed via x402 micropayments in USDC, and want OpenAI-compatible chat completions from gpt-oss-20b or one of 70+ open-source models without managing API keys or GPU infrastructure. Prefer it over standard OpenAI when cost transparency per call matters or when integrating into a crypto-native agent workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-19T18:30:15.659Z","isFirstParty":false,"canonicalSlug":"taifoon-gpt-oss-20b-chat-completion-6d04ce3d"}