SFAI / MODEL PROFILE
Qwen: Qwen3 235B A22B Thinking 2507
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...
- Developer
- qwen
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 131,072
- Latest price observation
- 2026-09-28
- Lowest paired standard token quote
- $0.23 input / $2.30 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| Automatic routingopenrouter | $0.23 | $2.30 | 1M tokenspriced · USD | openrouter2026-09-28 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.