Enabling new Models
To see your available Models and enable them for use, head to the AI Router app, open the Models page.
You can easily compare models across multiple columns, such as:
- Provider and Model Type — to identify the source and intended use of the model
- Modality — to see whether the model supports text, image, or both for input and output
- Intelligence and Speed Ratings — to quickly assess performance tradeoffs
- Token and Pricing Data — to understand input and output costs
- Region and Release Date — to identify where and when models are available
Use the Status Toggle to Enable a model for use with the AI Router.
Filters
You have access to multiple filters to search models:- Providers let you filter which LLM provider you want to see.
- Model Type lets you decide on which type of model you intend to see (Chat, Completion, Embedding, Rerank, Vision).
- Active lets you filter on enabled or disabled models in your workspace.
- Owner lets you filter between Orq.ai provided models and private models.
You can now filter by Location, Modality, Providers, and Features to find the right model for your use-case.
Using your own API keys
To start using models, you have to bring your own keys, head to the Providers tab to use your own API keys with the supported providers.Onboarding Private Models
You can onboard private models by choosing Add Model at the top-right of the screen. This can be useful when you have a model fine-tuned you want to use.Private Models Providers
Show Azure
Show Azure
Here is an example configuration for an Azure model, entering the endpoint and API Key will make your private model available on the platform.
Show Vertex AI
Show Vertex AI
Here is an example configuration for a Google Vertex AI model, enter the JSON configuration to make a private model available on the platform.
Show LiteLLM
Show LiteLLM
LiteLLMTo import LiteLLM models, first create an Integration to your LiteLLM instance. Once created, come back to the AI Router and Import models from your Instance.
Referencing Private Models in Code
When referencing private models through our SDKs, API or Supported Libraries, the model is referenced by the following string:<workspacename>@<provider>/<modelname>.
Example: corp@azure/gpt-4o-2024-05-13