Qwen2.5 Instruct 72B is a text-based AI model by Alibaba. It features 54 tok/s output speed, free pricing. It scores 15.6 on the intelligence index.
Output Speed
54 tok/s
Latency (TTFT)
1.10s
Blended Price
$0.00/M
| Input (Prompt) | Free |
| Output (Completion) | Free |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Qwen2.5 Instruct 72B is completely free to use.
Qwen2.5 Instruct 72B has a lower coding score of 11.9. For demanding coding tasks, consider a model with a higher coding benchmark.
Qwen2.5 Instruct 72B generates output at 54 tok/s. Time to first token is 1.10s.
Yes, Qwen2.5 Instruct 72B is available for free.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare Qwen2.5 Instruct 72B head-to-head with any model on our comparison page.