Qwen 3 235B A22B Instruct 2507
alibaba/qwen3-235b-a22b-2507- Alibaba
- Family · Qwen3
- Open weights
- Text → Text
- Tools · JSON
Spec & list price
Context256K
Max output16K
Input / 1M$0.09
Output / 1M$0.556.1× input
Usage
Tokens / day7.0B▼ 7.6% 7d
Usage rank#100
Requests / day1.9M
Tool calls / req0.05
Per request · 30 days
Avg input2.5K0.2× median
Avg output1670.2× median
Cache hit23%0.3× median
Tool-call failures1%0.5× median
Consumption
Peak 14.8B 29 SepLow 5.8B 1 NovRank today #100
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#314/33423 tok/s2.9× slower than median
Fastest provider35 tok/sbest of 3 providers
First token#520.49 s2.1× 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
- 107.5K · 814
Request parameters 17
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
+7 more
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Open-weight text assistants you can self-host
- Long document question answering
- Tool-calling agents with structured JSON output
- General chat and drafting over large context
Think twice for
- Image or video understanding (text-only input)
- Very large single responses (output cap is modest)
- New builds where newer family members fit better
Research papers
Same family
Qwen3- 7.2
- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
- 9.5
Using Qwen 3 235B A22B Instruct 2507 at volume?
Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.