OpenAI gpt-oss 120B

OpenAI gpt-oss 120B is a 120B open-weight language modelreleased under the Apache2.0 license. It is well-suited for reasoning and function calling use cases. Themodel is optimized for deployment on consumer hardware.

The 120B model achieves near-parity with OpenAI o4-mini on core reasoningbenchmarks, while running on a single 80GB GPU.

Managed API (MaaS) specifications

View model card in Model Garden

Model IDgpt-oss-120b-maas
Launch stageGA
Supported inputs & outputs
  • Inputs:
    Text
  • Outputs:
    Text
Capabilities
Consumption options
Versions
  • gpt-oss-120b-maas
    • Launch stage: GA
    • Release date: August 13, 2025
Supported regions

Model availability

  • Global
    • global
  • United States
    • us-central1

ML processing

  • United States
    • Multi-region
Limits

global:

  • Max output: 131,072
  • Context length: 131,072

us-central1:

  • Max output: 131,072
  • Context length: 131,072

PricingSeePricing.

Deploy as a self-deployed model

To self-deploy the model, navigate to thegpt-oss 120B 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.