Qwen3 Coder 480B A35B Instruct
by Abacus · family qwen · listed Jul 2025RTW
Qwen coding model for software agents, repository edits, and code reasoning
Current rates USD per 1M tokens
Input$0.29
Output$1.20
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/qwen3-coder-480b-a35b-instruct- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-07-22
- Last updated
- 2025-07-22
- Provider docs
- abacus.ai/help/api
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- SiliconFlow (China)$0.25 in · $1.00 out
- SiliconFlow$0.25 in · $1.00 out
- Jiekou.AI$0.29 in · $1.20 out
- LLM Gateway$0.30 in · $1.30 out
- NovitaAI$0.38 in · $1.55 out
- Cortecs$0.441 in · $1.98 out
- 302.AI$0.86 in · $3.43 out
- Alibaba (China)$0.861 in · $3.44 out
- Weights & Biases$1.00 in · $1.50 out
- Alibaba$1.50 in · $7.50 out
- Hugging Face$2.00 in · $2.00 out
- Qiniu— in · — out