{"uid":"cap_-E75HU1izZxFK7Mb6yLnp","slug":"multi-model-ai-gateway-agent402-arb-f5a8343c","name":"Multi-model AI Gateway (agent402-arb)","description":"LLM inference API: OpenAI-compatible chat completions for 136 AI models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM), paid per call in USDC on Base with x402. No account, no API key, automatic refund if the model fails.","url":"https://agent402-arb.rosariovitale0096.workers.dev/v1/chat/completions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","examples":["anthropic/claude-fable-5","anthropic/claude-fable-5.1","anthropic/claude-haiku-4.5","anthropic/claude-haiku-5.5","anthropic/claude-opus-4.5","anthropic/claude-opus-4.6","anthropic/claude-opus-4.7","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8-fast","anthropic/claude-opus-5","anthropic/claude-opus-5-fast","anthropic/claude-opus-5.5","anthropic/claude-opus-5.5-fast","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-5","anthropic/claude-sonnet-5.5","deepseek/deepseek-chat","deepseek/deepseek-reasoner","deepseek/deepseek-v3.2","deepseek/deepseek-v4-flash-0731","deepseek/deepseek-v4-flash-0731-fast","deepseek/deepseek-v4-flash-vision-exp","deepseek/deepseek-v4-pro","deepseek/deepseek-v4-pro-0813","deepseek/deepseek-v4.1-flash","google/gemini-2.5-flash","google/gemini-2.5-flash-lite","google/gemini-2.5-pro","google/gemini-3-flash-preview","google/gemini-3.1-flash-lite","openai/gpt-4.1","openai/gpt-4.1-mini","openai/gpt-4.1-nano","openai/gpt-4o","openai/gpt-4o-mini","openai/gpt-5-mini","openai/gpt-5.1","openai/gpt-5.2","openai/gpt-5.2-pro","openai/gpt-5.3-codex","openai/gpt-5.4","openai/gpt-5.4-mini","openai/gpt-5.4-nano","openai/gpt-5.4-pro","openai/gpt-5.5","openai/gpt-5.5-pro","openai/gpt-5.6-luna","openai/gpt-5.6-luna-pro","openai/gpt-5.6-sol","openai/gpt-5.6-sol-pro","openai/gpt-5.6-terra","openai/gpt-5.6-terra-pro","openai/gpt-6-astra","openai/gpt-6-astra-pro","openai/gpt-6-luna","openai/gpt-6-sol","openai/gpt-6.1-sol","openai/gpt-6.1-sol-ultrafast","openai/gpt-oss-120b"],"description":"Choose any current model; GET /v1/models for the live catalog."},"tools":{"type":"array"},"stream":{"type":"boolean","description":"true: server-sent events after payment"},"messages":{"type":"array","items":{"type":"object","required":["role"],"properties":{"role":{"enum":["system","user","assistant","tool","developer"],"type":"string"},"content":{"type":["string","array","null"]}}},"minItems":1},"max_tokens":{"type":"integer","maximum":16384,"minimum":1,"description":"Optional, default 4096"},"temperature":{"type":"number","maximum":2,"minimum":0},"response_format":{"type":"object"}}},"responseSchema":{"type":"json","example":{"id":"chatcmpl-7f3c2a91","model":"deepseek/deepseek-chat","usage":{"total_tokens":10,"prompt_tokens":9,"completion_tokens":1},"object":"chat.completion","choices":[{"index":0,"message":{"role":"assistant","content":"OK"},"finish_reason":"stop"}],"created":1791979200}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0014","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":"$0.0014/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0014","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0014","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_KL9D5doC346h5Q37bTIIH","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0014","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Routes OpenAI-compatible chat completion requests to a wide catalog of frontier AI models, billed per-call in USDC via x402 on Base/Arbitrum.","exampleAgentPrompt":"Using the multi-model gateway, send my message 'Explain quantum entanglement in simple terms' to google/gemini-2.5-pro and return the response — bill it per-call in USDC.","exampleUseCases":[{"title":"Comparing answers across frontier models","prompt":"Ask 'What are the top 3 risks of AGI development?' to both openai/gpt-4o and anthropic/claude-sonnet-4.5 using the pay-per-call gateway, then show me both responses side by side."},{"title":"Cost-efficient coding assistant","prompt":"Use openai/gpt-4.1-mini through the USDC inference gateway to review this Python function and suggest improvements — I want the cheapest capable model for code review tasks."},{"title":"Reasoning task with DeepSeek","prompt":"Send this math problem to deepseek/deepseek-reasoner via the multi-model gateway: 'A train leaves at 60 mph and another at 80 mph from 300 miles apart — when do they meet?' and give me the step-by-step solution."}],"resultDescription":"Returns an OpenAI-compatible chat completion object containing the assistant's reply message, the model used, token usage counts (prompt, completion, total), and finish reason. The response mirrors the standard /v1/chat/completions schema so it can be dropped into any OpenAI-compatible client.","failureModes":["Insufficient USDC balance — x402 payment fails before inference runs","Invalid model ID — returns error if model string not in current /models catalog (catalog may drift from schema enum)","Model unavailable — upstream provider outage causes 5xx from the gateway","Malformed messages array — missing required role/content fields returns 400","Stream=true not supported — schema enforces const:false, streaming requests rejected","Rate limits — upstream provider throttling may cause transient 429s"],"whenToPreferThis":"Choose this endpoint when you need pay-per-call access to a broad catalog of frontier models (Claude, GPT, Gemini, Grok, DeepSeek, Mistral, Qwen and more) without committing to individual provider subscriptions, and when your agent operates in a crypto-native environment capable of x402 USDC payments on Base or Arbitrum. It is especially useful when you want to switch models dynamically per request or compare outputs across providers from a single unified API surface.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T00:35:27.318Z","isFirstParty":false,"canonicalSlug":"multi-model-ai-gateway-agent402-arb-f5a8343c"}