Intelligence Index
019.5
> 21% OF MODELS
Qwen
Qwen3 235B A22B
Updated: September 2026
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Specifications
- Context
- 131K
- Input Modalities
- Text
- Output Modalities
- Text
- Input
- $0.455/M
- Output
- $1.82/M
Capabilities
TEXTWEBTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3.8 27B | Qwen | 262K | $0.45/M | $3.2/M |
| Kimi K2.5 | Moonshot | 262K | $0.45/M | $2.2/M |
| DeepSeek V4 Pro | DeepSeek | 1M | $0.435/M | $0.87/M |
| DeepSeek V4 Pro | DeepSeek | 1M | $0.435/M | $0.87/M |
| DeepSeek V4 Pro | DeepSeek | 1M | $0.435/M | $0.87/M |
Performance Metrics
Average Response Performance
- Output Speed
- 58.7 tok/s
- Time To First Token
- 2.73s
- Time To First Answer Token
- 36.82s
- End To End Response Time
- 45.34s
DATA SOURCE: Artificial Analysis