Qwen3 Coder 30B A3B Instruct
by ModelScope · family qwen · listed Jul 2025TW
Qwen coding model for software agents, repository edits, and code reasoning
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-Coder-30B-A3B-Instruct- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Apr 2025
- Released
- 2025-07-31
- Last updated
- 2025-07-31
- Provider docs
- modelscope.cn/docs/model-service/API-Inference/intro
Back of the envelope
≈
Also listed at
- Cortecs$0.053 in · $0.222 out
- Hugging Face$0.07 in · $0.26 out
- NovitaAI$0.07 in · $0.27 out
- SiliconFlow (China)$0.07 in · $0.28 out
- LLM Gateway$0.07 in · $0.27 out
- SiliconFlow$0.07 in · $0.28 out
- OVHcloud AI Endpoints$0.07 in · $0.26 out
- Kilo Gateway$0.07 in · $0.27 out
- OpenRouter$0.07 in · $0.27 out
- Helicone$0.10 in · $0.30 out
- NanoGPT$0.10 in · $0.40 out
- Clarifai$0.115 in · $0.748 out
- Scaleway$0.20 in · $0.80 out
- Alibaba (China)$0.216 in · $0.861 out
- Alibaba$0.45 in · $2.25 out