Qwen Plus 0728 (thinking)

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

ChatQwen1M tokens$0.2834 / $0.8502 · 1M

qwen/qwen-plus-2025-07-28:thinking

Context
1M tokens
Completion cap
32,768
Tools
Yes
JSON
Yes
Released
2025-09-08

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/qwen-plus-2025-07-28:thinking",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen Plus 0728 (thinking)?
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination. Qwen Plus 0728 (thinking) runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen-plus-2025-07-28:thinking.
Is Qwen Plus 0728 (thinking) free?
No. Input is $0.2834 per 1M tokens and output is $0.8502 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen Plus 0728 (thinking)?
Qwen Plus 0728 (thinking) has a 1M tokens context window. It supports up to 32,768 completion tokens.
Does Qwen Plus 0728 (thinking) support tool calling and structured outputs?
Qwen Plus 0728 (thinking) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen Plus 0728 (thinking) released?
Qwen Plus 0728 (thinking) was released on 2025-09-08.

More models from Qwen