Qwen3 Next 80B A3B Thinking
alibaba/qwen3-next-80b-a3b-thinking- Alibaba
- Family · Qwen3 Next
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context256K
Max output236K
Input / 1M$0.15
Output / 1M$1.208× input
Usage
Requests / day13
Tool calls / req0.15
Per request · 30 days
Avg input2.5K0.2× median
Avg output2.9K4.2× median
Reasoning share89%1.6× median
Tool-call failures2.4%1.3× median
Consumption
Peak 77.5M 8 OctLow 5.0K 21 Oct
News & trends
News · latest from Alibaba
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Qwen3.8-Flash Now Available in the EU on Alibaba Cloudtwitter.com · 31 Oct
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
Benchmarks
Benchmark data: Artificial AnalysisFamily progress
Intelligence Index
- Family releases11.2
Technical details
- Tokenizer
- Qwen3
- Knowledge cutoff
- 2025-09-30
- License
- Apache 2.0
- Parameters
- 81.3B
- Moderation
- none
- Downloads · likes
- 43.5K · 503
Request parameters 17
- tools
- tool_choice
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
+7 more
- stop
- seed
- frequency_penalty
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Self-hosted reasoning with efficient inference
- Long document reasoning and Q&A
- Agents that plan with tool calls
- Very large reasoning outputs
Think twice for
- Latency-sensitive interactive chat
- Image understanding
- High-volume simple chat
Same family
Qwen3 Next- 9.6
- 11.2
Want Qwen3 Next 80B A3B Thinking on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.