If you are using the Playground, you can now utilize Playground memory. This feature enables you to add historical context when comparing different models simultaneously.

Added support for Dall-E models in the Playground and Deployments for OpenAI and Azure.

We added a new Integrations section to allow the use of your API keys. At the moment, we support custom API keys from the following LLM providers

Now, it is possible to reset the parameters of the primary model and the fallback model in a Deployment.

Recently, we've expanded our platform's capabilities by adding AWS Bedrock models. You can now explore these models in the Playground or integrate them into your deployments.