Intelligence Index
0112.7
> 32% OF MODELS
Qwen
Qwen3 235B A22B Thinking 2507
Updated: September 2026
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...
Specifications
- Context
- 131K
- Input Modalities
- Text
- Output Modalities
- Text
- Input
- $0.23/M
- Output
- $2.3/M
Capabilities
TEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 14B | Qwen | 131K | $0.2275/M | $0.91/M |
| Qwen3 Coder | Qwen | 262K | $0.22/M | $1/M |
| Qwen3 Coder | Qwen | 262K | $0.22/M | $1/M |
| Qwen3 Coder | Qwen | 262K | $0.22/M | $1/M |
| Qwen3 Coder | Qwen | 262K | $0.22/M | $1/M |
Performance Metrics
Coding Index
0222.1
> 22% OF MODELS
Agentic Index
031.3
> 14% OF MODELS
DATA SOURCE: Artificial Analysis