API Calls
This page covers all model capabilities of the platform, mapping one-to-one to the categories in Models. Start with the endpoint quick reference, then dive into the calling details of each capability as needed.
Endpoint Quick Reference
For available models and real-time prices of each endpoint, see the Model Plaza; for model categories, billing methods, and naming conventions, see Models; for authentication, see Base URL & Authentication.
Capability Pages
- Text Chat: chat, multi-turn, streaming
- Vision Understanding (Multimodal): image understanding, video understanding
- Embeddings & Rerank: embeddings, rerank
- Audio: text-to-speech, music generation (Volcengine async tasks / MiniMax format), speech-to-text
- Image Generation: text-to-image, image-to-image, Seedream layer decomposition, Image Editing, Vega async tasks
- Video Generation: async tasks (Sora / Kling / Jimeng / Doubao / MiniMax format / Kling unified format)
