Qwen3 Coder 480B A35B
by Weights & Biases · family qwen · listed Jul 2025TW
Mixture-of-Experts model optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning.
Current rates USD per 1M tokens
Input$1.00
Output$1.50
Cache read$1.00
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-Coder-480B-A35B-Instruct- Context window
- 262K tokens
- Max output
- 262K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Apr 2025
- Released
- 2025-07-22
- Last updated
- 2025-07-22
- Provider docs
- docs.wandb.ai/guides/integrations/inference/
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- 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
- Jiekou.AI$0.29 in · $1.20 out
- Abacus$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