qwen/qwen3.8-2.4t-a95b

Qwen: Qwen3.8 2.4T A95B

Context length
1049K
Input / 1M tokens
$2.00
Output / 1M tokens
$6.00
Released
2026-08-12
Modality
text->text

About Qwen: Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Call Qwen: Qwen3.8 2.4T A95B

Via OpenRouter: one base URL for every provider.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-2.4t-a95b",
    "messages": [{"role": "user", "content": "Say hello"}]
  }'

Direct on Qwen / Alibaba DashScope (Model Studio):

curl https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-2.4t-a95b",
    "messages": [{"role": "user", "content": "Say hello"}]
  }'

Qwen / Alibaba DashScope (Model Studio) keys

OpenRouter keys

OpenRouter keys work for qwen/qwen3.8-2.4t-a95b regardless of the upstream provider.