Qwen: Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
Qwen3 Coder 30B A3B Instruct is a 30B open-weight model (3B active per token), ranking #185 of 235 on the TryAii Score. It's served by 5 independent hosts from $0.07/$0.28 per million input/output tokens — about a third of what models at its level usually charge. It's reasonably quick at roughly 24-68 tokens/sec.
Prompt $/1M
$0.070
Completion $/1M
$0.280
Context
262,144 tok
Best provider
100 tok/s · Ambient
Specs
- Model id
- qwen/qwen3-coder-30b-a3b-instruct
- Display name
- Qwen: Qwen3 Coder 30B A3B Instruct
- Modality
- text->text
- Tokenizer
- Qwen3
- Instruct type
- —
- Context length
- 262,144
- Max completion
- 235,929
- Prompt $/1M
- $0.070
- Completion $/1M
- $0.280
- Free tier
- no
Capabilities
- Function callingyes
- JSON modeno
- System promptno
- 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 |
|---|---|
| Ambientfastest | 100 |
| Nebiusfastest | 75 |
| Novitafastest | 49 |
| Alibaba | 36 |
| SiliconFlow | 20 |
| DigitalOcean | 14 |
| qwenfastest | — |
| Artificial Analysis | 0 |