Qwen3 Coder

Qwen3 Coder is a large-scale, open-weight modeldeveloped for advanced software development tasks. The model's key feature isits large context window, allowing it to process and understand large codebasescomprehensively.

Managed API (MaaS) specifications

View model card in Model Garden

Model IDqwen3-coder-480b-a35b-instruct-maas
Launch stageGA
Supported inputs & outputs
  • Inputs:
    Text,Code
  • Outputs:
    Text,Code
Capabilities
Consumption options
Versions
  • qwen3-coder-480b-a35b-instruct-maas
    • Launch stage: GA
    • Release date: August 13, 2025
Supported regions

Model availability

  • United States
    • us-south1
  • Global
    • global

ML processing

  • United States
    • Multi-region
Limits

us-south1:

  • Max output: 65,536
  • Context length: 262,144

global:

  • Max output: 65,536
  • Context length: 262,144

PricingSeePricing.

Deploy as a self-deployed model

To self-deploy the model, navigate to theQwen3 Coder model card in the Model Gardenconsole and clickDeploy model. For more information about deploying andusing partner models, seeDeploy a partner model and make predictionrequests.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-02-19 UTC.