Bring Your Own LLM
Wren AI can run on the LLM provider of your choice. Connect one or more providers and route different parts of the AI pipeline to the models you prefer — using guided quick-setup templates or fully manual configuration.
Availability
Bring Your Own LLM is available exclusively on the Enterprise Plus plan of the Wren AI Self-Hosted Version.
Supported providers
Wren AI supports a wide range of LLM providers and deployment options, including:
- OpenAI
- Azure OpenAI
- Anthropic Claude (via AWS Bedrock)
- Google Gemini (via Vertex AI)
- Local and custom models — self-hosted or privately deployed models

Get started
Our team works with you on model selection, configuration, and pipeline assignments to fit your environment and requirements.
Interested in bringing your own LLM? Contact us to learn more about setup details and our recommendations.