{"uid":"cap_VBkM2YPO1HELaJ5K4WaqG","slug":"telnyx-x402-gateway-qwen3-235b-chat-completions-aa910b2d","name":"Telnyx x402 Gateway – Qwen3-235B Chat Completions","description":"Pay USDC per request for Telnyx Inference and Audio (text-to-speech, speech-to-text) through x402.","url":"https://x402.telnyx.com/v1/chat/completions/_t/qwen3-235b?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"n":{"type":"integer","const":1,"description":"Fixed to one completion per paid call."},"model":{"type":"string","const":"Qwen/Qwen3-235B-A22B","description":"Model identifier; fixed to Qwen/Qwen3-235B-A22B on this route."},"tools":{"type":"array","items":{"type":"object"},"maxItems":16},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant","tool"],"type":"string"},"content":{"type":"string","maxLength":8000}}},"maxItems":32,"description":"OpenAI-style chat messages."},"max_tokens":{"type":"integer","maximum":2048,"minimum":1},"temperature":{"type":"number","maximum":2,"minimum":0}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-xxx","usage":{"total_tokens":16,"prompt_tokens":12,"completion_tokens":4},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"Hello!"},"finish_reason":"stop"}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.010497","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":"$0.010497/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.010497","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.010497","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JXN9EXuOscXT_kuptgMFS","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.010497","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generate AI chat completions using Qwen/Qwen3-235B-A22B via Telnyx's x402 gateway, paying $0.01 USDC per request on-chain","exampleAgentPrompt":"Send my conversation to Qwen3-235B on Telnyx and generate a reply — the system prompt is 'You are a helpful coding assistant', the user message is 'Explain async/await in Python in 3 bullet points', use temperature 0.7 and max 512 tokens, and pay the ~$0.01 USDC fee per request.","exampleUseCases":[{"title":"Agentic tool-calling with Qwen3","prompt":"I need to run a multi-turn conversation with Qwen3-235B where the assistant can call a weather tool I've defined — send the system message 'You are a helpful assistant with tool access', the user message 'What's the weather in Berlin?', include my weather tool schema, and keep the response under 1024 tokens. Pay the per-call USDC fee automatically."},{"title":"Pay-per-use coding help","prompt":"Ask Qwen3-235B to review this Python function and suggest improvements — system prompt: 'You are a senior Python engineer', user message: 'Here is my code: [paste code]', temperature 0.3, max 2048 tokens. I want to pay only for this one call without any monthly subscription."},{"title":"Crypto-native AI pipeline for content draft","prompt":"Generate a short product description for my new SaaS tool using Qwen3-235B — system: 'You are a marketing copywriter', user: 'Write a 3-sentence product description for a project management app called TaskFlow that targets remote teams', temperature 1.0, max 300 tokens. Use the Telnyx x402 gateway so each generation is billed in USDC."}],"resultDescription":"Returns an OpenAI-compatible chat completion JSON object containing the assistant's message content, finish reason (e.g. 'stop'), a completion ID, and token usage breakdown (prompt tokens, completion tokens, total tokens).","failureModes":["Insufficient USDC balance causes payment failure and 402 response before inference runs","Messages array exceeds 32 items or individual content exceeds 8000 characters, returning 400 validation error","max_tokens exceeds 2048 ceiling, causing schema validation rejection","Model identifier mismatch if caller tries to override the fixed Qwen/Qwen3-235B-A22B model field","Network timeout if the 235B model is under high load, causing incomplete response","Tools array exceeds 16 items, triggering a validation error"],"whenToPreferThis":"Choose this endpoint when you need a powerful Mixture-of-Experts LLM (Qwen3-235B with 22B active parameters) on a strict pay-per-call basis with no monthly commitment, billed in USDC via x402 micropayments. It is ideal for agentic workflows that need tool calling, sporadic high-quality inference without subscription overhead, or crypto-native pipelines where on-chain payment provenance matters. Prefer alternatives when you need streaming responses, more than 2048 output tokens, or a different model family.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T12:35:19.321Z","isFirstParty":false,"canonicalSlug":"telnyx-x402-gateway-qwen3-235b-chat-completions-aa910b2d"}