OpenAI gpt-oss 120B

OpenAI gpt-oss 120B is a 120B open-weight language model released under the Apache 2.0 license. It is well-suited for reasoning and function calling use cases. The model is optimized for deployment on consumer hardware.

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

View model card in Model Garden

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

Model availability
  • Global
    • global endpoint
  • United States
    • us-central1

ML processing
  • United States
    • Multi-region
Quota limits

global endpoint:

  • Max output: 32,768
  • Context length: 131,072

us-central1:

  • Max output: 32,768
  • Context length: 131,072
Pricing See Pricing.

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

Last updated 2025年10月16日 UTC.