Gemini Enterprise Agent Platform supports a curated list of open models as managed models. These open models can be used with Gemini Enterprise Agent Platform as a model as a service (MaaS) and are offered as a managed API. When you use a managed open model, you continue to send your requests to Gemini Enterprise Agent Platform endpoints. Managed open models are serverless, so there's no need to provision or manage infrastructure.

Managed open models can be discovered using Model Garden. You can also deploy models using Model Garden. For more information, see Explore AI models in Model Garden.

Before you can use open models, you need to grant user access to open models.

Open models

The following open models are offered as managed APIs on Gemini Enterprise Agent Platform Model Garden (MaaS):

The following open embedding models are offered as managed APIs on Gemini Enterprise Agent Platform Model Garden (MaaS):

Model name	Description	Output dimensions	Max sequence length	Supported text languages	Quickstart
multilingual-e5-small	Part of the E5 family of text embedding models. Small variant contains 12 layers.	Up to 384	512 tokens	Supported languages	Model card
multilingual-e5-large	Part of the E5 family of text embedding models. Large variant contains 24 layers.	Up to 1024	512 tokens	Supported languages	Model card

Open model regulatory compliance

The certifications for Generative AI on Gemini Enterprise Agent Platform continue to apply when open models are used as a managed API using Gemini Enterprise Agent Platform. If you need details about the models themselves, additional information can be found in the respective model card, or you can contact the respective model publisher.

Your data is stored at rest within the selected region or multi-region for open models on Gemini Enterprise Agent Platform, but the regionalization of data processing may vary. For a detailed list of open models' data processing commitments, see Data residency for open models.

Customer prompts and model responses are not shared with third parties when using the Gemini Enterprise API, including open models. Google only processes customer data as instructed by the customer, which is further described in our Cloud Data Processing Addendum.

Context caching

Context caching helps reduce the cost and latency of requests to Open Models that contain repeated content. This is enabled while using pay-as-you-go traffic only, and doesn't support other traffic types, such as Provisioned Throughput and Batch.

The supported type of caching is implicit caching, which is automatic caching that's enabled in all Google Cloud projects by default and provides a 90% discount on cached tokens compared to standard input tokens when cache hits occur. With this type of caching, you don't define and call the caches explicitly. Instead, our backend pulls from these caches once repeated context is detected.

Supported models

• qwen3-coder-480b-a35b-instruct-maas
• kimi-k2-thinking-maas
• minimax-m2-maas
• gpt-oss-20b-maas
• deepseek-v3.1-maas
• deepseek-v3.2-maas
• gemma-4-26b-a4b-it-maas
• glm-5-maas
• glm-5.2-maas

The cachedContentTokenCount field in your response's metadata indicates the number of tokens in the cached part of your input. Caching requests must contain a minimum of 4096 tokens (this minimum is subject to change during Preview).

When enabled, implicit cache hit cost savings are automatically passed on to you. Cache hits aren't guaranteed and are dependent on requests sent and other factors. To increase the chances of an implicit cache hit, try the following:

• Place large and common contents at the beginning of your prompt.
• Send requests with a similar prefix in a short amount of time.

What's next

• Before using open models, Grant user access to open models.
• Learn how to Call open model APIs.