Qwen3.8 Max API
Qwen3.8-Max is Alibaba's flagship Qwen3.8 model: 2.4T total parameters with about 95B active, a 1M-token context window, native multimodal understanding, and strong coding, vision and long-horizon agent results. The launch announcement said weights were scheduled for release; do not call it open source without checking the current licence.
Official source: model page · verified 2026-10-22
Pricing
Prices can change with upstream providers; the rate at settlement is authoritative.
Call the API
Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.
curl https://api.kimiseek.app/v1/chat/completions \
-H "Authorization: Bearer $KIMISEEK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-max",
"messages": [{"role": "user", "content": "Hello from KimiSeek"}]
}'Where it fits
Best for
- Quality-first multimodal assistants
- Complex coding and long-horizon agent tasks
- Vision, document and long-video understanding
Tradeoffs
- Premium pricing versus Qwen3.8 Flash
- Very large model; overkill for routine chat and extraction
Model details
FAQ
Is Qwen3.8-Max multimodal?
Yes. Alibaba describes it as a multimodal foundation with visual intelligence, in addition to text.
Are the weights open?
The August launch announcement said weights were scheduled for release. Verify the current official licence and weight page before making an open-source claim.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to qwen3.8-max with your KimiSeek API key.