Anthropic
qwen3.8-flash
qwen/qwen3.8-flash
Price per million tokens
- Input
- $0.177
- Output
- $0.555
- Cache write
- $0.236
- Cache read
- $0.019
What you pay, and your usage page shows what we paid beside what you paid on every request you send.
Limits
- Context window
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Images
- supported
What it costs to run
| Workload | Input | Output | Cost | Per 1,000 calls |
|---|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0005 | $0.45 |
| Long document summary | 50,000 | 2,000 | $0.0100 | $9.97 |
| Agent step with tools | 20,000 | 1,500 | $0.0044 | $4.38 |
| 1M in, 1M out | 1,000,000 | 1,000,000 | $0.7326 | $732.59 |
Calling it
const res = await client.chat.completions.create({ model: "qwen/qwen3.8-flash", messages: [{ role: "user", content: "Hello" }], });