Qwen3.8 2.4T A95B (batch)

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 suited for coding, research, complex reasoning, and agentic workflows.

ChatQwen1M tokens$2.7251 / $6.8129 · 1M

qwen/qwen3.8-2.4t-a95b:batch

Context
1M tokens
Completion cap
909,000
Tools
Yes
JSON
Yes
Released
2026-08-12

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.8-2.4t-a95b:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3.8 2.4T A95B (batch)?
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 suited for coding, research, complex reasoning, and agentic workflows. Qwen3.8 2.4T A95B (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3.8-2.4t-a95b:batch.
Is Qwen3.8 2.4T A95B (batch) free?
No. Input is $2.7251 per 1M tokens and output is $6.8129 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3.8 2.4T A95B (batch)?
Qwen3.8 2.4T A95B (batch) has a 1M tokens context window. It supports up to 909,000 completion tokens.
Does Qwen3.8 2.4T A95B (batch) support tool calling and structured outputs?
Qwen3.8 2.4T A95B (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3.8 2.4T A95B (batch) released?
Qwen3.8 2.4T A95B (batch) was released on 2026-08-12.

More models from Qwen