Qwen3 Coder 480B A35B Instruct
by Nvidia · family qwen · listed Jul 2025T
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-480b-a35b-instruct- Context window
- 262K tokens
- Max output
- 67K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- Apr 2025
- Released
- 2025-07-23
- Last updated
- 2025-07-23
- Provider docs
- docs.api.nvidia.com/nim/
Back of the envelope
≈
Also listed at
- LLM Gateway$0.22 in · $1.80 out
- Merge Gateway$0.22 in · $1.80 out
- SiliconFlow$0.25 in · $1.00 out
- SiliconFlow (China)$0.25 in · $1.00 out
- Abacus$0.29 in · $1.20 out
- Jiekou.AI$0.29 in · $1.20 out
- NovitaAI$0.38 in · $1.55 out
- DevPass (LLM Gateway)$0.38 in · $1.55 out
- 302.AI$0.86 in · $3.43 out
- Alibaba (China)$0.861 in · $3.44 out
- Alibaba$1.50 in · $7.50 out
- Eden AI$1.50 in · $7.50 out
- Hugging Face$2.00 in · $2.00 out
- Qiniu— in · — out