Qwen 3 235b A22B 2507 Thinking
by NanoGPT · family qwen · listed Jul 2025TW
Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use
Current rates USD per 1M tokens
Input$0.30
Output$0.50
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen/qwen3-235b-a22b-thinking-2507- Context window
- 131K tokens
- Max output
- 82K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-07-25
- Last updated
- 2025-07-25
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- ModelScopefree in · free out
- IO.NET$0.11 in · $0.60 out
- submodel$0.20 in · $0.60 out
- Eden AI$0.23 in · $2.30 out
- Qiniu$0.29 in · $2.90 out
- Jiekou.AI$0.30 in · $3.00 out
- Hugging Face$0.30 in · $3.00 out
- Kilo Gateway$0.45 in · $3.50 out
- OpenRouter$0.45 in · $3.50 out
- Venice AI$0.45 in · $3.50 out