Thanks so much. I tried it out and wasn't able to get it to work. Below is code within my librechat.yaml file. I tried out my creds using a curl and it worked. I even tried to hardcode the keys into the file, but it wouldn't get the Portkey endpoint to show up on my end. I may be getting the model name wrong, but am not sure. I am trying to integrate it with a virtual key that has access to AWS Bedrock.

Let me know if you have any suggestions on what else I should try.

custom:

• name: "Portkey"
  baseURL: "${PORTKEY_GATEWAY_URL}"
  headers:
  x-portkey-api-key: "${PORTKEY_API_KEY}"
  x-portkey-virtual-key: "${PORTKEY_VIRTUAL_KEY}"
  models:
  default: ["anthropic.claude-v2:1"]
  fetch: true
  titleConvo: true
  titleModel: "current_model"
  summarize: false
  summaryModel: "current_model"
  forcePrompt: false
  modelDisplayLabel: "Portkey"

Is it possible to set usage limits on a per user basis? Specifically, using the user attribute from "x-portkey-metadata: {"_user"

Hi all, is it possible to fetch all models we have access to via cURL (or SDK)?