Qwen 3 Coder 480B
by NanoGPT · family qwen · listed Mar 2026TW
Qwen coding model for software agents, repository edits, and code reasoning
Current rates USD per 1M tokens
Input$0.13
Output$0.50
Cache read$0.065
Cache write—
Against the market
On the record
- Model id
qwen/qwen3-coder- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-03-17
- Last updated
- 2026-03-17
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Helicone$0.22 in · $0.95 out
- OpenRouter$0.30 in · $1.00 out
- FastRouter$0.30 in · $1.20 out
- OpenCode Zen$0.45 in · $1.80 out
- Kilo Gateway$0.975 in · $4.88 out
- Vercel AI Gateway$1.50 in · $7.50 out