Qwen3.8 Flash API
Qwen3.8-Flash is the throughput-oriented Qwen3.8 model, with native image, text and video input, a 1M-token context, a 131K output ceiling, and compatibility with both OpenAI and Anthropic protocols. It is positioned for coding, agents and visual understanding at high concurrency.
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-flash",
"messages": [{"role": "user", "content": "Hello from KimiSeek"}]
}'Where it fits
Best for
- High-volume multimodal chat and extraction
- Coding assistance and agent sub-tasks
- Applications that need OpenAI or Anthropic compatibility
Tradeoffs
- Less quality headroom than Qwen3.8-Max
- Use Max when the output is customer-facing or unusually complex
Model details
FAQ
Does Qwen3.8-Flash accept images and video?
Yes. The official model page lists image, text and video input, with text output.
Which protocols are supported?
The official page lists OpenAI and Anthropic compatibility, useful for Claude Code and similar tools.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to qwen3.8-flash with your KimiSeek API key.