Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

ChatQwen131k tokens$0.496 / $1.9839 · 1M

qwen/qwen3-235b-a22b

Context
131k tokens
Completion cap
8,192
Tools
Yes
JSON
Yes
Released
2025-04-28

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/qwen3-235b-a22b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3 235B A22B?
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling. Qwen3 235B A22B runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-235b-a22b.
Is Qwen3 235B A22B free?
No. Input is $0.496 per 1M tokens and output is $1.9839 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3 235B A22B?
Qwen3 235B A22B has a 131k tokens context window. It supports up to 8,192 completion tokens.
Does Qwen3 235B A22B support tool calling and structured outputs?
Qwen3 235B A22B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3 235B A22B released?
Qwen3 235B A22B was released on 2025-04-28.

More models from Qwen