# Model Access Gateway – Pay-Per-Call LLM Chat Completions (x402/USDC) > Model Access Gateway – Pay-Per-Call LLM Chat Completions (x402/USDC) is a paid API for AI agents from modelaccessgateway.com, paid per call via x402, $0.0014/call, status unknown (last checked 2026-10-18). OpenAI-compatible chat completions API supporting 136 AI models (Claude, GPT, Gemini, DeepSeek, Grok, etc.), paid per call in USDC on Base via x402 with no account or API key required. ## Facts - Endpoint: POST https://modelaccessgateway.com/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/model-access-gateway-pay-per-call-llm-chat-completions-x402-usdc-b1c6696a - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_dIiFUNL1sJH67fYr2JYNV 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 model-access-gateway-pay-per-call-llm-chat-completions-x402-usdc-b1c6696a -d '' ``` Example prompt: Using the Model Access Gateway, send a chat completion request to DeepSeek deepseek-chat asking it to summarize the following text in three bullet points, and pay per call in USDC with no API key needed: 'Blockchain technology enables decentralized trust...' ## When to prefer this Choose this endpoint when you need anonymous, accountless LLM inference across a wide range of frontier models and want to pay per call in USDC rather than managing API keys or subscriptions. Ideal for autonomous AI agents that self-fund their own inference costs, for prototyping across multiple model families without multi-provider onboarding, or for use cases where crypto-native micropayments (x402/Base) are preferred over traditional billing. Prefer over direct provider APIs when you want a single OpenAI-compatible interface covering Claude, GPT, Gemini, DeepSeek, and others simultaneously. ## Known failure modes - Payment insufficient or x402 transaction fails — request rejected before inference - Model identifier not found — returns error; use GET /v1/models for live catalog - Model provider upstream outage — automatic refund issued to caller - Streaming connection dropped mid-response — partial content delivered - Malformed messages array — validation error returned - Rate limiting by upstream provider — transient failure, may retry ## How this service works 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. ## Output Returns an OpenAI-format chat completion JSON object containing the assistant's message content, model name, usage statistics (prompt tokens, completion tokens, total tokens), finish reason, and a unique completion ID. Supports streaming via server-sent events when stream=true. An automatic USDC refund is issued if the model fails to respond. ## 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/model-access-gateway-pay-per-call-llm-chat-completions-x402-usdc-b1c6696a/health.json - [Zero catalog index](https://www.zero.xyz/llms.txt) - [Other services from modelaccessgateway.com](https://www.zero.xyz/host/modelaccessgateway.com/llms.txt)