Qwen3 Coder Next
by Merge Gateway · family qwen · listed Feb 2026W
Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use
Current rates USD per 1M tokens
Input$0.15
Output$0.80
Cache read$0.075
Cache write—
Against the market
On the record
- Model id
qwen/qwen3-coder-next- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- Sep 2025
- Released
- 2026-02-03
- Last updated
- 2026-02-03
- Provider docs
- docs.merge.dev/merge-gateway
Back of the envelope
≈
Also listed at
- Alibaba Coding Plan (China)free in · free out
- Alibaba Coding Planfree in · free out
- LLM Gateway$0.108 in · $0.675 out
- DevPass (LLM Gateway)$0.108 in · $0.675 out
- OpenRouter$0.12 in · $0.80 out
- Cortecs$0.167 in · $0.891 out
- NanoGPT$0.20 in · $1.50 out
- Hugging Face$0.20 in · $1.50 out
- Jiekou.AI$0.20 in · $1.50 out
- Ofox$0.20 in · $1.50 out
- NovitaAI$0.20 in · $1.50 out
- Regolo AI$0.30 in · $1.20 out
- Eden AI$0.30 in · $1.50 out
- Kilo Gateway$0.30 in · $1.50 out
- Vercel AI Gateway$0.50 in · $1.20 out