Qwen3.6 Max Preview
by NanoGPT · family qwen · listed Apr 2026
Flagship Qwen model for complex reasoning, coding, and agentic workflows
Current rates USD per 1M tokens
Input$1.04
Output$6.24
Cache read$0.52
Cache write—
Against the market
On the record
- Model id
qwen3.6-max-preview- Context window
- 246K tokens
- Max output
- 66K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- Apr 2025
- Released
- 2026-04-20
- Last updated
- 2026-04-20
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- OpenRouter$1.03 in · $6.16 out
- Kilo Gateway$1.03 in · $6.16 out
- Pioneer$1.04 in · $6.24 out
- AIHubMix$1.27 in · $7.61 out
- LLM Gateway$1.30 in · $7.80 out
- Alibaba$1.30 in · $7.80 out
- DevPass (LLM Gateway)$1.30 in · $7.80 out
- Merge Gateway$1.31 in · $7.88 out
- Alibaba (China)$1.32 in · $7.90 out
- Ofox$2.15 in · $12.86 out