Qwen: Qwen3 14B
qwen/qwen3-14b
Qwen3 14B (Qwen) is a compact 14B open-weight model priced near the bottom of the board, at $0.12/$0.24 per million input/output tokens, served by 2 independent hosts. For the money it delivers #211 of 260 on the TryAii Score. Its best showing is #15 on MATH. It's reasonably quick at roughly 61-64 tokens/sec.
Prompt $/1M
$0.120
Completion $/1M
$0.240
Context
40,960 tok
Best provider
66 tok/s · NextBit
Specs
- Model id
- qwen/qwen3-14b
- Display name
- Qwen: Qwen3 14B
- Modality
- text->text
- Tokenizer
- Qwen3
- Instruct type
- qwen3
- Context length
- 40,960
- Max completion
- 16,384
- Prompt $/1M
- $0.120
- Completion $/1M
- $0.240
- 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 |
|---|---|
| NextBitfastest | 66 |
| DeepInfra | 59 |