x402.press Qwen
simple-inference

Qwen

Qwen AI inference without an API key or credit card. Pay per request in USDC or EURC on any of 7 chains. OpenAI-compatible chat completions endpoint.

inferenceqwenllmaix402openai-compatible

What is Qwen?

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; bills one flat amount per chain on the DeepSeek tier, which is 25% above x402.press/deepseek's cheapest flash quote — its off-peak price for a small prompt — on every chain both services answer for, measured from both 402 handshakes on 2026-10-31, and that service prints its own per-chain amounts at https://x402.press/services/deepseek/ — because DeepSeek prices flash by prompt size and peak window, so its quote meets and passes this flat price for a larger prompt or in peak hours) and qwen3.8-max (flagship for complex reasoning; billed on the Exclusive tier, the highest tier). The 402 payment challenge always carries the exact price for the model you request. A metered (`upto`) accept is also offered: authorize the prompt plus your `max_tokens` as a ceiling and settle the measured input and output tokens, never above that ceiling. Nothing in the metered path caps context or output. No API keys, no accounts, no subscriptions. A drop-in replacement for OpenAI client libraries: point your existing OpenAI SDK at https://x402.press/qwen/v1 and it works, with all OpenAI-compatible parameters (temperature, max_tokens, top_p, etc.) forwarded to the underlying model.

Pay per call in USDC, EURC across Base, Arbitrum, Polygon, Avalanche, Ethereum, Robinhood and Arc via the x402 micropayment protocol — no subscriptions, no API keys, no wallets to configure for the caller.

Operations

inference

MethodEndpointDescriptionTier
POST/v1/chat/completionsOpenAI-compatible chat completions. Price follows the requested model: qwen3.8-flash bills one flat amount per chain on the DeepSeek tier — 25% above x402.press/deepseek's cheapest flash quote (its off-peak price for a small prompt) on every chain both services answer for, measured from both 402 handshakes on 2026-10-31 (that service prints its own per-chain amounts); DeepSeek prices flash by prompt size and peak window, so it costs more than this flat price for a larger prompt or in peak hours. 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.deepseek

Data sources

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."
    }
  ]
}