Qwen3 235B (Qwen3-235B-A22B-Instruct-2507)

Qwen3 235B (Qwen3-235B-A22B-Instruct-2507) is a large 235B parameter model. The model is distinguished by its "hybrid thinking" capability, which allows users to dynamically switch between a methodical, step-by-step "thinking" mode for complex tasks like mathematical reasoning and coding, and a rapid "non-thinking" mode for general-purpose conversation. Its large context window makes it suitable for use cases requiring deep reasoning and long-form comprehension.

View model card in Model Garden

Property Description
Model ID qwen3-235b-a22b-instruct-2507-maas
Versions
  • qwen3-235b-a22b-instruct-2507-maas
    • Launch stage: GA
    • Release date: August 13, 2025
Supported regions

Model availability

  • United States
    • us-south1

ML processing

  • United States
    • Multi-region
Quota limits

us-south1:

  • QPM: 20
  • Input TPM: 170,000
  • Output TPM: 15,000
  • Max output: 16,384
  • Context length: 262,144

Pricing See Pricing.