Provider updates on Portkey ⚙️

We’ve rolled out several upgrades across major providers to make your LLM integrations faster, more flexible, and production-ready:

OpenAI & Azure OpenAI: Added support for streaming audio transcription requests.

Vertex AI: Added custom model support for batch inference.

Support for input_audio parameter to enable richer context in requests

Support for anthropic-beta header

AWS Bedrock: Added global profile support for Bedrock models.

Added name field mapping for /messages endpoint document objects.

Streamlined token counting endpoint to use invoke mode for better compatibility.

Added pass-through parameters for Bedrock batch create endpoints.

Azure:

Improved Azure Entra caching for better performance.

Added pricing support for image editing models across OpenAI, Azure OpenAI, and Azure Foundry providers.