{"uid":"cap_Je7oK-ksu6srjWbVPyNpQ","slug":"taifoon-chat-completions-hy4-preview-model-871cd6f9","name":"Taifoon Chat Completions – hy4-preview Model","description":"OpenAI-compatible chat completion on tencent/Hy4-preview, served by DeepInfra (serverless inference) and sold by Taifoon at the provider's price plus a 20 % reseller cut: 1.0008 / 3.0012 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/hy4-preview?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_yKcX3aeqixSV2aGsTr6km","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 pay-per-call chat completion endpoint serving 71 LLMs via the Taifoon coordination layer, defaulting to NVIDIA-Nemotron-3-Nano-4B-BF16","exampleAgentPrompt":"Ask the Taifoon hy4-preview endpoint to answer this for me using the phi-4 model, up to 200 tokens: 'Explain the difference between supervised and unsupervised learning in two sentences.'","exampleUseCases":[{"title":"Quick open-model text summarization","prompt":"Summarize this paragraph using the qwen2.5-7b-instruct model and keep the response under 300 tokens: 'The Federal Reserve raised interest rates by 25 basis points citing persistent inflation pressures and a resilient labor market, signaling it may hold rates elevated through the end of the year.'"},{"title":"Code explanation with Llama 3","prompt":"Use llama-3.1-8b-instruct to explain what this Python function does in plain English, no more than 150 tokens: 'def fib(n): return n if n <= 1 else fib(n-1) + fib(n-2)'"},{"title":"Low-cost LLM for agent reasoning step","prompt":"I need a cheap LLM call using the gemma-3-12b-it model — ask it to classify this customer message as 'complaint', 'inquiry', or 'compliment', max 50 tokens: 'Your shipping took three weeks and the package arrived damaged.'"}],"resultDescription":"A JSON chat completion object in OpenAI format containing: an ID, the model used, the assistant's reply message, finish reason (e.g. 'stop'), prompt/completion/total token counts, and a created timestamp. The choices array contains the generated text content.","failureModes":["Missing or invalid x402 payment header returns 402 Payment Required","messages array empty or missing causes 422 validation error","max_tokens exceeds 700 causes schema rejection","Invalid model name falls back to default or returns 400","Rate limiting or quota exhaustion from the coordination layer returns 429","Network timeout on the underlying inference provider returns 504"],"whenToPreferThis":"Choose this endpoint when you need cheap, pay-per-call LLM inference across a wide selection of open-weight models (71 options) without a subscription, and you want OpenAI-compatible request/response format. Especially useful for agents that need to route through different models dynamically or want micro-payment billing via x402. Prefer over OpenAI directly when cost per call matters and open-source models are acceptable.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-20T06:35:40.124Z","isFirstParty":false,"canonicalSlug":"taifoon-chat-completions-hy4-preview-model-871cd6f9"}