Qwen 4 Max
by NanoGPT · family qwen · listed Nov 2026RTV
Flagship multimodal model for coding, office productivity, frontend design, and complex agentic tasks
Current rates USD per 1M tokens
Input$1.41
Output$4.24
Cache read$0.071
Cache write$1.77
Against the market
On the record
- Model id
qwen/qwen4-max- Context window
- 1M tokens
- Max output
- 131K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-11-16
- Last updated
- 2026-11-16
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Novita AI$1.41 in · $4.24 out
- Deep Infra$1.41 in · $4.24 out
- OpenRouter$1.43 in · $4.28 out
- DevPass (LLM Gateway)$1.45 in · $4.25 out
- LLM Gateway$1.45 in · $4.25 out
- Vercel AI Gateway$1.50 in · $4.50 out
- Kilo Gateway$1.50 in · $4.50 out
- OpenCode Go$1.50 in · $4.50 out
- Charm Hyper$1.50 in · $4.50 out
- Ofox$1.50 in · $4.50 out
- Eden AI$1.50 in · $4.50 out
- EmpirioLabs AI$1.50 in · $4.50 out
- CrossModel$1.60 in · $4.80 out