# Multi-model AI Gateway (agent402-arb) > Multi-model AI Gateway (agent402-arb) is a paid API for AI agents from agent402-arb.rosariovitale0096.workers.dev, paid per call via x402, $0.0014/call, status unknown (last checked 2026-10-18). Routes OpenAI-compatible chat completion requests to a wide catalog of frontier AI models, billed per-call in USDC via x402 on Base/Arbitrum. ## Facts - Endpoint: POST https://agent402-arb.rosariovitale0096.workers.dev/v1/chat/completions?utm_source=zero.xyz - Price: $0.0014/call - Payment: x402 - Status: unknown - Last checked: 2026-10-18 - Activations on Zero: 0 - Tags: x402 - Canonical page: https://www.zero.xyz/c/multi-model-ai-gateway-agent402-arb-f5a8343c - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-E75HU1izZxFK7Mb6yLnp Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently. ## How to call it through Zero Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`): ```sh zero fetch --capability multi-model-ai-gateway-agent402-arb-f5a8343c -d '' ``` Example prompt: 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. ## When to prefer this 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. ## Known failure modes - 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 ## How this service works LLM inference API: OpenAI-compatible chat completions for 100+ AI models (DeepSeek, GPT, Claude, Gemini, Grok, GLM, Qwen, Kimi, Llama, Mistral). Suited for AI agents that need on-demand text generation, coding or tool calling paid per request in USDC on Base with x402: no account, no API key. Model in body.model (GET /v1/models); streaming supported. Exact price in the 402 quote; automatic refund if the model fails. ## Output 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. ## Request schema (JSON Schema) ```json { "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", … (truncated) ``` ## Response schema (JSON Schema) ```json { "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 } } ``` ## More - Live health (JSON, refreshed every minute): https://www.zero.xyz/c/multi-model-ai-gateway-agent402-arb-f5a8343c/health.json - [Zero catalog index](https://www.zero.xyz/llms.txt) - [Other services from agent402-arb.rosariovitale0096.workers.dev](https://www.zero.xyz/host/agent402-arb.rosariovitale0096.workers.dev/llms.txt)