Qwen3 30B A3B Instruct 2507
Qwen3 30B A3B Instruct 2507 is a mixture-of-experts language model developed by Qwen. It is designed for high-quality instruction following and multilingual tasks, utilizing a large context window to process extensive text inputs.
Qwen3 30B A3B Instruct 2507 specs and pricing
- Provider: Qwen
- Released: July 29, 2025
- Context window: 262K tokens
- Max output: 236K tokens
- Input: text
- Output: text
- Price: $0.10 input / $0.30 output per 1M tokens
- Tool calling: yes
What Qwen3 30B A3B Instruct 2507 is good at
- Complex instruction following tasks
- Processing large volumes of text
- Multilingual content generation
To-dos to try with Qwen3 30B A3B Instruct 2507
- Summarize the key arguments from a 200,000-word technical report.
- Translate a long document into multiple languages while maintaining specific formatting instructions.
- Draft a comprehensive project plan based on a series of detailed instructional prompts.
FAQ
- What is the architecture of this model? This model is a mixture-of-experts language model with 30.5 billion total parameters and 3.3 billion active parameters per inference.
- Does this model support tool calling? Yes, Qwen3 30B A3B Instruct 2507 is capable of tool calling.
- How much does Qwen3 30B A3B Instruct 2507 cost? Qwen3 30B A3B Instruct 2507 costs $0.10 per million input tokens and $0.30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.32 credits ($1 = 100 credits).
- What is the context window of Qwen3 30B A3B Instruct 2507? Qwen3 30B A3B Instruct 2507 can read up to 262K tokens at once and write up to 236K tokens in one reply.
- Can I use Qwen3 30B A3B Instruct 2507 without coding? Yes. In todo.is you pick Qwen3 30B A3B 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.