Qwen3 235B A22B Instruct 2507
Qwen3 235B A22B Instruct 2507 is a multilingual language model developed by Qwen. It uses a mixture-of-experts architecture to handle general-purpose text generation tasks and supports tool calling. The model features a large context window of 262,144 tokens.
Qwen3 235B A22B Instruct 2507 specs and pricing
- Provider: Qwen
- Released: July 21, 2025
- Context window: 262K tokens
- Max output: 118K tokens
- Input: text
- Output: text
- Price: $0.14 input / $0.80 output per 1M tokens
- Tool calling: yes
What Qwen3 235B A22B Instruct 2507 is good at
- Complex multilingual text generation
- Tasks requiring long-form document processing
- Applications needing integrated tool usage
To-dos to try with Qwen3 235B A22B Instruct 2507
- Summarize a 200,000-token technical manual and extract all safety protocols.
- Translate a multi-page document into five different languages while maintaining tone.
- Use tool calling to search a database and format the results into a structured report.
FAQ
- What is the primary architecture of this model? It is a multilingual, instruction-tuned mixture-of-experts model based on the Qwen3-235B architecture.
- Does this model support tool calling? Yes, the model is designed to support tool calling for interactive tasks.
- How much does Qwen3 235B A22B Instruct 2507 cost? Qwen3 235B A22B Instruct 2507 costs $0.14 per million input tokens and $0.80 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.5 credits ($1 = 100 credits).
- What is the context window of Qwen3 235B A22B Instruct 2507? Qwen3 235B A22B Instruct 2507 can read up to 262K tokens at once and write up to 118K tokens in one reply.
- Can I use Qwen3 235B A22B Instruct 2507 without coding? Yes. In todo.is you pick Qwen3 235B A22B Instruct 2507 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.