{"uid":"cap_jaaqcpw3JTWVuUX1sS4qb","slug":"taifoon-chat-completions-glm-5-1-model-a7e61f44","name":"Taifoon Chat Completions – GLM-5.1 Model","description":"One API over the coordination layer: the root that commits every chain, proofs that a transaction happened, what every route costs, the transfers, and the agent-hiring lifecycle. Most operations are public reads. Writes say who may make them in `security` (RelayerKey = X-API-Key, OperatorToken = x-operator-token) and in x-taifoon-auth.rule; nothing here signs or sends a transaction for you. A 2xx JSON object answered to a caller that sent no key also carries `get_key` (and the headers x-taifoon-get-key and Link rel=free-key): how to get a free key in one call; proofs, evidence packs, cards and this document are left as written. Lineage language: a sale walks offer in → classify → listed → hired → delivered → graded → settled → legs written → accrued → split → PAID → recorded; a venue adapter has offer.in · offer.out · job.in · job.out; the seller of record pays on by forward · share · period · markup; a leg is Owed → Reserved → Sent | Held | Refunded; a hop reads OK · HELD · MISSING · BROKEN. On the wire the hop ids are the event field step and the metric label stage; a wire name is never renamed.","url":"https://coord.taifoon.dev/v1/chat/completions/glm-5.1?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":"0.0008","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_Z91xeoziqLTDO1bYNt3qL","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":"Serves OpenAI-compatible chat completions via Taifoon's coordination layer using the GLM-5.1 model (or any of 71 available models), paid per-call with USDC via x402.","exampleAgentPrompt":"Use the Taifoon coordination layer to send a chat message asking 'What is the capital of France?' to the mistral-small-24b-instruct-2501 model, with a max of 200 tokens.","exampleUseCases":[{"title":"Quick LLM answer via micropayment","prompt":"Ask the Taifoon API to answer 'Explain the difference between TCP and UDP in two sentences' using the llama-3.1-8b-instruct model, with a max of 150 tokens — I want to pay per call, no subscription."},{"title":"Open-source model comparison run","prompt":"Send the same prompt 'Write a haiku about the ocean' to Taifoon using the gemma-3-27b-it model with max 100 tokens, so I can compare its output to what I got from a smaller model."},{"title":"Agentic sub-task LLM call","prompt":"Have Taifoon call the qwen2.5-7b-instruct model with the system message 'You are a JSON formatter' and user message 'Format this as JSON: name Alice age 30 city Berlin', max 300 tokens."}],"resultDescription":"A JSON chat completion object in OpenAI format, including the assistant's reply text under choices[0].message.content, the model name used, prompt/completion/total token counts, a unique completion ID, and the finish reason (e.g. 'stop').","failureModes":["Missing or invalid x402 payment header returns 402 Payment Required","Invalid model name returns an error or falls back to default NVIDIA Nemotron model","messages array empty or exceeds 32 items causes validation failure","max_tokens outside 1–700 range causes rejection","No API key with write operations returns 401/403; reads may succeed with get_key hint in response","Upstream model provider unavailable causes 5xx error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible chat completions on a pay-per-call basis (USDC via x402) without committing to a subscription, or when you want access to a wide roster of 71 open-source and proprietary models (Llama, Mistral, Gemma, Qwen, DeepSeek, Phi, GLM) through a single endpoint. Prefer it over standard OpenAI when you need micropayment-native LLM inference or want to pick from open-weight models not available on OpenAI directly.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-18T00:56:22.730Z","isFirstParty":false,"canonicalSlug":"taifoon-chat-completions-glm-5-1-model-a7e61f44"}