External Models

Before defining a custom external model provider, check your project settings to see if the provider you’re looking for is already supported.

To use a custom external model from a cloud provider that OpenPipe doesn’t support, you can add an external model provider to your project. External models can be used for the following purposes:

• Proxying chat completions
• Filtering and relabeling your data
• Evaluating outputs through criteria

The instructions below demonstrate how to add a DeepSeek (OpenAI Compatible) and Azure provider to your project.

Creating an external model provider

Find the External Model Providers section of your project settings, and click the Add Provider button.

Give your custom provider a slug, API key, and add a custom base url if necessary. The provider slug should be unique, and will be used when we proxy requests to models associated with this provider.

DeepSeek (OpenAI Compatible)

Adding a model to the external provider

To add a model to the provider you’re creating, click the Add Model button.

Provide a slug that matches the model you’d like to call on your external provider. To call gpt-4o-2024-08-06 on Azure for instance, the slug should be gpt-4o-2024-08-06.

DeepSeek (OpenAI Compatible)

Setting input cost and output cost is optional, but can be helpful for showing relative costs in the evals page.

We currently support custom external models for providers with openai and azure-compatible endpoints. If you’d like support for an external provider with a different API format, send a request to [e-mail].