diff --git a/docs/my-website/img/release_notes/lb_batch.png b/docs/my-website/img/release_notes/lb_batch.png new file mode 100644 index 00000000000..05e430ef49f Binary files /dev/null and b/docs/my-website/img/release_notes/lb_batch.png differ diff --git a/docs/my-website/release_notes/v1.69.0-stable/index.md b/docs/my-website/release_notes/v1.69.0-stable/index.md index 62d5791bb92..0b11cb9cfb5 100644 --- a/docs/my-website/release_notes/v1.69.0-stable/index.md +++ b/docs/my-website/release_notes/v1.69.0-stable/index.md @@ -45,18 +45,40 @@ pip install litellm==1.69.0.post1 LiteLLM v1.69.0-stable brings the following key improvements: -- **Email Invites**: Send new users onboarded to LiteLLM an email invite. +- **Email Invites 2.0**: Send new users onboarded to LiteLLM an email invite. +- **Loadbalance Batch API Models**: Easily loadbalance across multiple azure batch deployments using LiteLLM Managed Files - **Nscale**: LLM API for compliance with European regulations. -- **Bedrock /v1/messages**: Use Bedrock Anthropic models with /v1/messages. +- **Bedrock /v1/messages**: Use Bedrock Anthropic models with Anthropic's /v1/messages. ## Email Invites -This new release brings support for: -- Sending email invites for new users added to LiteLLM. -- Sending a user their virtual key over email. -- Controlling email notification settings. -- Support for SMTP servers or Resend for sending emails. + +This release brings the following improvements to our email invite integration: +- New templates for user invited and key created events. +- Fixes for using SMTP email providers. +- Native support for Resend API. +- Ability for Proxy Admins to control email events. + +For LiteLLM Cloud Users, please reach out to us if you want this enabled for your instance. + +## Batch API Load Balancing + + + + +This release brings LiteLLM Managed File support to Batches. This is great for: + +- Proxy Admins: You can now control which Batch models users can call. +- Developers: You no longer need to know the Azure deployment name when creating your batch .jsonl files - just specify the model your LiteLLM key has access to. + +Over time, we expect LiteLLM Managed Files to be the way most teams use Files across `/chat/completions`, `/batch`, `/fine_tuning` endpoints. ## New Models / Updated Models - **Gemini ([VertexAI](https://docs.litellm.ai/docs/providers/vertex#usage-with-litellm-proxy-server) + [Google AI Studio](https://docs.litellm.ai/docs/providers/gemini))**