Alibaba/ Qwen
Qwen3 235B A22B Thinking 2507
alibaba/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...
Released
2025-07-25
Context window
262K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-235b-a22b-thinking-2507
- Knowledge cutoff
- 2025-06-30
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-235b-a22b-thinking-2507 | openai_chat | 262K | - | Text | Text | ReasoningTool callTemperatureOpen weight | Hugging Face: Qwen/Qwen3-235B-A22B-Thinking-2507 | input $0.23/M output $2.3/M | Yes |
| Kilo Gateway | qwen/qwen3-235b-a22b-thinking-2507 | openai_chat | 262K | - | Text | Text | ReasoningTool callTemperatureOpen weight | - | input $0.23/M output $2.3/M | Yes |
| NovitaAI | qwen/qwen3-235b-a22b-thinking-2507 | openai_chat | 262K | - | Text | Text | ReasoningTool callTemperatureOpen weight | - | input $0.3/M output $3/M | Yes |
| Jiekou.AI | qwen/qwen3-235b-a22b-thinking-2507 | openai_chat | 262K | - | Text | Text | ReasoningTool callTemperatureOpen weight | - | input $0.3/M output $3/M | Yes |
Capabilities
ReasoningTool callTemperatureOpen weight