Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000045 | $0.450 |
| completion | 0.0000035 | $3.50 |
{
"temperature": null,
"top_p": null,
"frequency_penalty": null
}