Qwen 3 235B A22B Thinking 2507
alibaba/qwen3-235b-a22b-thinking-2507- Alibaba
- Family · Qwen3
- Open weights
- Text → Text
- Tools
Not on OSMEXO yet
Spec & list price
Context125K
Max output16K
Input / 1M$0.45
Output / 1M$3.507.8× input
Usage
Tokens / day282.7M▲ 22% 7d
Usage rank#249
Requests / day30.4K
Tool calls / req0.11
Per request · 30 days
Avg input6.2K0.4× median
Avg output2.9K4.2× median
Cache hit22%0.3× median
Reasoning share80%1.4× median
Tool-call failures1.3%0.7× median
Consumption
Peak 342.8M 26 SepLow 15.0M 17 OctRank today #249
News & trends
184 mentions this week ▲ 36%Qwen3 family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 family
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard453 upvotes
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard416 points
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted edits26 points
- New Card for Qwen3.8 27b and MiniMax H3632 upvotes
- Qwen 3.8 27B vs Strata Coder - Local LLM battle75.2K views
- DavidAU Qwen3.8 27B Turbo Brilliance 50X-Reasoning... tested - Local LLM setup87.7K views
News · latest from Qwen3
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
- How to train your own Jev for $17Together AI · 23 Sep
Benchmarks
Benchmark data: Artificial AnalysisOutput speed#51/334116 tok/s1.8× faster than median
First token#730.56 s1.8× quicker than median
Family progress
Intelligence Index
- Family releases33.7
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-06-30
- License
- Apache 2.0
- Parameters
- 235B
- Moderation
- none
- Downloads · likes
- 10.4K · 419
Request parameters 11
- tools
- tool_choice
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
- stop
- frequency_penalty
+1 more
- presence_penalty
When to use
Best for
- Hard math and science reasoning
- Multi-step planning for agents
- Self-hosted deep reasoning
- Complex analysis where latency is acceptable
Think twice for
- High-volume simple chat
- Latency-sensitive interactive apps
- Strict schema-bound structured output
- Image understanding
Research papers
Same family
Qwen3- 7.2
- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
Want Qwen 3 235B A22B Thinking 2507 on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.