Qwen3.8 Max
by AIHubMix · family qwen · listed Aug 2026RT
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Current rates USD per 1M tokens
Input$1.69
Output$5.07
Cache read$0.169
Cache write$2.11
Against the market
On the record
- Model id
qwen3.8-max- Context window
- 991K tokens
- Max output
- 128K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-08-03
- Last updated
- 2026-08-03
- Provider docs
- docs.aihubmix.com
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- Deep Infra$1.65 in · $4.95 out
- Alibaba (China)$1.78 in · $5.33 out
- SCX.ai$1.81 in · $5.45 out
- LLM Gateway$1.81 in · $5.45 out
- CrossModel$1.88 in · $5.63 out
- NanoGPT$2.00 in · $6.00 out
- OpenRouter$2.00 in · $6.00 out
- OpenCode Go$2.00 in · $6.00 out
- Merge Gateway$2.00 in · $6.00 out
- DigitalOcean$2.00 in · $6.00 out
- Alibaba$2.00 in · $6.00 out
- Ofox$2.00 in · $6.00 out
- Requesty$2.00 in · $6.00 out