Generate
Chat, image generation, and audio speech endpoints.
Capabilities
A growing toolkit for your next AI feature.
Build with chat, image understanding, audio, embeddings, document analysis, and video endpoints when a compatible model is enabled.
- Chat and text
- Image and document understanding
- Audio, embeddings, and video workflows
Chat & text
Image understanding
Audio & speech
Embeddings
PDF analysis
Video workflows
Availability depends on the enabled model and its supported modalities.
How it comes together
One gateway, several useful building blocks.
Use each endpoint where it belongs, then verify modality support for the model you plan to call.
Understand
Vision, document, and video analysis workflows.
Represent
Embeddings for retrieval and similarity tasks.
A listed endpoint does not mean every model supports it. Check model input and output modalities first.