Qwen3.5 122B A10B
alibaba/qwen3.5-122b-a10b- Alibaba
- Family · Qwen3
- Released 24 Feb 2026
- Open weights
- Text · Image · Video → Text
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context256K
Max output64K
Input / 1M$0.26
Output / 1M$2.088× input
Scores · standing
Intelligence17.7#156/490
Coding45.7#77/196
Usage
Tokens / day518.2M▼ 14% 7d
Usage rank#228
Requests / day49.1K
Tool calls / req0.17
Per request · 30 days
Avg input6.0K0.4× median
Avg output9161.3× median
Cache hit0%0.0× median
Reasoning share73%1.3× median
Tool-call failures4.6%2.5× median
Consumption
Peak 3.7B 19 OctLow 383.7M 25 OctRank today #228
News & trends
201 mentions this week ▲ 49%Qwen3 family · videos, posts, articles · 30 days
Trending · 14 days · Qwen3 family
- Qwen3.8 27b (Q6) casually breaking reCAPTCHA838 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 H3656 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
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 4 providers, latest day
Output speed#165/33463 tok/sabout median
Fastest provider98 tok/sbest of 4 providers
First token#1761.16 sabout median
#15 cheapest of 21 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Family progress
Intelligence Index
- Family releases33.7
Technical details
- Tokenizer
- Qwen3
- License
- Apache 2.0
- Parameters
- 125B
- Moderation
- none
- Downloads · likes
- 994.4K · 652
Request parameters 19
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- min_p
+9 more
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Agentic workflows with heavy tool calling
- Instruction-following pipelines with strict formats
- Long document Q&A over large inputs
- Multimodal analysis of images and video
- Self-hosted deployments (open weights)
Think twice for
- Image or video generation
- Audio input or output
- Very long single outputs
- Lowest-cost bulk classification
Research papers
Same family
Qwen3- 7.2
- 6.0
- 6.9
- 6.1
- 5.2
- 13.1
Alternatives
other vendors · similar capability- 21.8
- 13.1
- 21.5
- 22.2
Want Qwen3.5 122B A10B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.