Qwen3-235B-A22B-Thinking-2507
by ModelScope · family qwen · listed Jul 2025RTW
Qwen reasoning model for deliberate problem solving, math, and coding
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-235B-A22B-Thinking-2507- Context window
- 262K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Apr 2025
- Released
- 2025-07-25
- Last updated
- 2025-07-25
- Provider docs
- modelscope.cn/docs/model-service/API-Inference/intro
Back of the envelope
≈
Also listed at
- iFlowfree in · free out
- Weights & Biases$0.10 in · $0.10 out
- IO.NET$0.11 in · $0.60 out
- Kilo Gateway$0.11 in · $0.60 out
- SiliconFlow (China)$0.13 in · $0.60 out
- SiliconFlow$0.13 in · $0.60 out
- OpenRouter$0.149 in · $1.50 out
- submodel$0.20 in · $0.60 out
- LLM Gateway$0.20 in · $0.60 out
- Hugging Face$0.30 in · $3.00 out
- NovitaAI$0.30 in · $3.00 out
- Jiekou.AI$0.30 in · $3.00 out
- NanoGPT$0.30 in · $0.50 out
- Venice AI$0.45 in · $3.50 out
- Qiniu— in · — out