Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

OpenAI gpt-oss 20B

Caution: As of July 21, 2026, the gpt-oss-20b-maas endpoint is deprecated and will be retired on October 21, 2026. For more information, see Open model deprecations.

OpenAI gpt-oss 20B is a 20B 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 20B model delivers similar results to OpenAI o3-mini on common benchmarks and can run on edge devices with 16GB of memory, making it ideal for on-device use cases, local inference, or rapid iteration without costly infrastructure.

Managed API (MaaS) specifications

Pricing

Model ID	`gpt-oss-20b-maas`
Modalities	Text Input and output Image Not supported Audio Not supported Video Not supported
Capabilities	Function calling Supported Structured output Supported Thinking Not supported
Consumption options	Provisioned Throughput Not supported Batch inference Supported Pay-as-you-go Standard PayGo Supported Fixed quota Supported
Supported regions	Model availability	United States: `us-central1`
Supported regions	ML processing	Multi-region: `us`
Quotas	`us-central1`: 32,768 maximum output, 131,072 context length
Versions	`gpt-oss-20b-maas` Launch stage: GA Release date: August 13, 2025

Deploy as a self-deployed model

To self-deploy the model, navigate to the gpt-oss 20B model card in the Model Garden console and click Deploy model. For more information about deploying and using partner models, see Deploy a partner model and make prediction requests.