Qwen: Qwen2.5 7B Instruct
qwen/qwen-2.5-7b-instruct
Qwen2.5 7B Instruct (Qwen) is a compact 7B open-weight model priced near the bottom of the board, at $0.1/$0.2 per million input/output tokens, served by 1 independent host. For the money it delivers #247 of 260 on the TryAii Score. Its best showing is #7 on DROP. It's among the fastest models we track, at about 125 tokens/sec.
Prompt $/1M
$0.100
Completion $/1M
$0.200
Context
32,768 tok
Best provider
125 tok/s · Phala
Specs
- Model id
- qwen/qwen-2.5-7b-instruct
- Display name
- Qwen: Qwen2.5 7B Instruct
- Modality
- text->text
- Tokenizer
- Qwen
- Instruct type
- chatml
- Context length
- 32,768
- Max completion
- 29,491
- Prompt $/1M
- $0.100
- Completion $/1M
- $0.200
- 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 |
|---|---|
| Phalafastest | 125 |