---
title: "OpenAI-Compatible LLM Gateway ($0.015/call)"
method: POST
path: "/v1/chat/completions"
tags: ["llm", "gateway", "openai-compatible", "chat-completions", "inference", "claude", "completion", "ai", "proxy", "no-account"]
---

# OpenAI-Compatible LLM Gateway ($0.015/call)

`POST /v1/chat/completions`

## Request

- Base URL: `https://x402.shizu.me`
- URL: `https://x402.shizu.me/v1/chat/completions`
- Auth: none declared

Drop-in OpenAI Chat Completions — point any OpenAI SDK's base_url here and pay per call in USDC, no account or key. POST {model, messages:[{role,content}], max_tokens?, temperature?, stream?}. Backed by Claude Haiku; flat price regardless of model. Multi-turn (system/user/assistant), OpenAI-shaped choices[]+usage. Input ~3000 words, output capped 512 tokens. The account-less inference gateway for looping agents.

Paid endpoint: $0.015 per call via the x402 protocol (USDC on Base). An unpaid request returns 402 with payment requirements in the PAYMENT-REQUIRED response header; attach payment and retry.

## Response `200`

Paid result (JSON)

## Other responses

- `402`: Payment required — x402 requirements in the PAYMENT-REQUIRED response header

---

[API](https://skmtc.dev/shizu/apis/scrape402.md) · [All operations](https://skmtc.dev/shizu/apis/scrape402/llms.txt) · [OpenAPI document](https://skmtc.dev/shizu/apis/scrape402/revisions/0852d74798b8?raw)