Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
Qwen2.5 72B Instruct is a 72B open-weight model, ranking #198 of 234 on the TryAii Score. Its best showing is #9 on LiveBench. It's served by 2 independent hosts from $0.36/$0.4 per million input/output tokens — about half of what models at its level usually charge.
Prompt $/1M
$0.360
Completion $/1M
$0.400
Context
32,768 tok
Best provider
21 tok/s · Novita
Specs
- Model id
- qwen/qwen-2.5-72b-instruct
- Display name
- Qwen2.5 72B Instruct
- Modality
- text->text
- Tokenizer
- Qwen
- Instruct type
- chatml
- Context length
- 32,768
- Max completion
- 16,384
- Prompt $/1M
- $0.360
- Completion $/1M
- $0.400
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Novitafastest | 21 |
| DeepInfra | 16 |