# Qwen
> Qwen AI inference without an API key or credit card. Pay per request in USDC or EURC on any of 4 chains. OpenAI-compatible chat completions endpoint.

OpenAI-compatible AI inference via x402 micropayments. Proxies requests to Alibaba DashScope's international OpenAI-compatible API, supporting two models — qwen3.8-flash (fast, cost-effective; billed on the DeepSeek tier, the same price as deepseek.x402.press) and qwen3.8-max (flagship for complex reasoning; billed on the Exclusive tier, the highest tier — the same price as /ask endpoints across the network). The 402 payment challenge always carries the exact price for the model you request. No API keys, no accounts, no subscriptions. A drop-in replacement for OpenAI client libraries: point your existing OpenAI SDK at https://qwen.x402.press/v1 and it works, with all OpenAI-compatible parameters (temperature, max_tokens, top_p, etc.) forwarded to the underlying model.

## Pricing
- `deepseek` tier — **$0.00875** on Base: `/v1/chat/completions`
- Chains: Base, Arbitrum, Polygon, Avalanche. Per-chain prices in `/.well-known/x402.json`.

## Operations
### inference
- **POST /v1/chat/completions** — OpenAI-compatible chat completions. Price follows the requested model: qwen3.8-flash bills on the DeepSeek tier (same price as deepseek.x402.press), qwen3.8-max bills on the Exclusive tier (highest tier). Additional OpenAI parameters (temperature, max_tokens, top_p, frequency_penalty, presence_penalty, stop, etc.) are forwarded. — params: `model` (string)*, `messages` (array)* (tier: `deepseek`)

## Data sources
- Alibaba DashScope API (dashscope-intl.aliyuncs.com) — Proxied server-side; the service's own API key is never exposed to callers. International endpoint.

## Free endpoints
- GET `/`, `/health`, `/about`, `/.well-known/x402.json`, `/llms.txt`, `/openapi.json` (standard)
- GET `/v1/models` — List available models (qwen3.8-flash, qwen3.8-max)
- GET `/qwen/feedback` — Return the 50 most recent feedback entries
- POST `/qwen/feedback` — Submit feedback (response_id, rating 1-5, optional comment)

## Examples
- `chat_completions` — Ask a question via the OpenAI-compatible endpoint (economy model): `{"model": "qwen3.8-flash", "messages": [{"role": "user", "content": "What is the capital of France?"}]}`
- `chat_completions` — Complex reasoning (flagship model, Exclusive-tier price): `{"model": "qwen3.8-max", "messages": [{"role": "user", "content": "Prove that sqrt(2) is irrational."}]}`