ALAlibaba/ Qwen
Qwen3 235B A22B Instruct 2507
alibaba/qwen3-235b-a22b-instruct-2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
Model information
Released
2025-07-21
Context window
262K
Max output
33K
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-235b-a22b-2507
- Knowledge cutoff
- 2025-06-30
Resources
Capabilities
Open weightStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-235b-a22b-2507 | openai_chat | 262K | 33K | Tool callStructuredTemperature | Hugging Face: Qwen/Qwen3-235B-A22B-Instruct-2507 | input $0.15/M · output $0.598/M | Yes | ||
| TensorX | qwen/qwen3-235b-a22b-2507 | openai_chat | 262K | 33K | Tool callTemperature | - | input $0.072/M · output $0.464/M cache read $0.018/M · cache write $0.09/M | Yes | ||
| Kilo Gateway | qwen/qwen3-235b-a22b-2507 | openai_chat | 262K | 33K | Tool callStructuredTemperature | - | input $0.15/M · output $0.598/M | Yes | ||
| Alibaba | qwen3-235b-a22b-2507 | custom | 262K | 33K | - | - | - | Yes |