Models / qwen-flash

qwen-flash API

Qwen model qwen-flash through AZET’s OpenAI-compatible API: $0.0404 input and $0.3234 output per 1M tokens, with a 1,000,000 token context. Prepaid USD credit, billed per token, no subscription.

Model idqwen-flash
Price$0.0404 in / $0.3234 out per 1M tokens
Context1,000,000 tokens

Call qwen-flash

RequestcURL
curl https://api.azet.io/v1/chat/completions -H "Authorization: Bearer $AZET_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "qwen-flash", "messages": [{"role": "user", "content": "Hello"}]}'

Same request and response shape as OpenAI Chat Completions. Base URL https://api.azet.io/v1 · Authorization: Bearer azk_….

qwen-flash pricing

USD per 1M tokensInputOutput
Input up to 256,000 tokens$0.0404$0.3234
Input up to 1,000,000 tokens$0.2021$1.617
Cached input$0.0081—
Maker’s own list price$0.05$0.40

GET /v1/models/qwen-flash · The price at the time of the request applies.

Questions

How much does qwen-flash cost on AZET?

qwen-flash costs $0.0404 input and $0.3234 output per 1M tokens on the AZET AI API, and $0.0081 per 1M cached input tokens. The maker’s own list price is $0.05 input and $0.40 output; AZET never charges more than that.

Is qwen-flash OpenAI-compatible on AZET?

Yes. Set the base URL to https://api.azet.io/v1 in any OpenAI SDK, LangChain or LiteLLM and use the model id qwen-flash. POST /v1/chat/completions takes the same request and returns the same response shape, with streaming.

What is the context window of qwen-flash?

1,000,000 tokens.

How do I pay for qwen-flash?

With prepaid USD credit from $5, billed per token. There is no subscription and no monthly minimum.

All models → · API reference → · Buy credit →

Questions or a team account? hello@azet.io
Service status Status
Full reference API reference
Connect these docs to your AI llms.txt