Qwen2.5 72B Instruct
alibaba/qwen-2.5-72b-instruct- Alibaba
- Family · Qwen2
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context32K
Max output16K
Input / 1M$0.36
Output / 1M$0.401.1× input
Usage
Tokens / day334.6M▲ 8.6% 7d
Usage rank#242
Requests / day171.9K
Tool calls / req0.01
Per request · 30 days
Avg input1.4K0.1× median
Avg output1350.2× median
Tool-call failures4%2.1× median
Consumption
Peak 744.9M 8 OctLow 178.5M 31 OctRank today #242
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 AnalysisOutput speed#315/33420 tok/s3.2× slower than median
First token#1440.92 s1.2× quicker than median
Family progress
Intelligence Index
- Family releases7.7
Technical details
- Tokenizer
- Qwen
- Knowledge cutoff
- 2024-06-30
- License
- other
- Parameters
- 72.7B
- Moderation
- none
- Downloads · likes
- 191.5K · 1.0K
Request parameters 15
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
+5 more
- seed
- frequency_penalty
- logit_bias
- presence_penalty
- repetition_penalty
When to use
Best for
- Self-hosted general-purpose assistants
- Multilingual chat and content writing
- Structured JSON extraction
- Fine-tuning on an open base
Think twice for
- Long document Q&A
- New builds (newer Qwen models exist)
- Image understanding
Same family
Qwen2- 6.3
- 6.9
- 7.7
Want Qwen2.5 72B Instruct on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.