Table of contents

• Contact Us
• 🧠 Introduction

Quickstart

• Setting Up
• Supported SDKs

API Overview

• Text Models (LLM)
  • Completion or Chat Models
  • Parameters
  • Chat Completion
  • Function Calling
    • Image-To-Text (Vision)
    • Anthropic
  • Managing Assistants & Threads
    • Threads
      • Runs
      • Messages
  • Embeddings
• Image Models
  • Generate an Image
  • Supported Models
• Vision Models
  • Image Analysis
  • OCR: Optical Character Recognition
  • OFR: Optical Feature Recognition
• Audio Models (Music & Vocal)
  • Suno AI v2
    • What is a Clip
    • Costs
    • Clip Generation
      • Generate with GPT
      • Fetch Clips
      • Generate with Custom Lyrics
      • Clip Continuation / Extension
    • Lyrics Generation
      • Generate Lyrics
      • Fetch Lyrics
  • Suno AI v1 (legacy)
    • Generate an Audio
    • Custom Audio Generation
    • Fetch Generations
    • Extend an Audio
• Speech Models
  • Speech-to-Text (STT)
  • Text-to-Speech (TTS)
• Video Models
  • Luma AI v2
    • Overview
    • Generate Video
    • Fetch Generations
    • Extend Video
  • Luma AI v1 (legacy)
    • Luma AI Text-to-Video
• Model Database
  • Text Models
  • Video Models
  • Image Models
  • Vision Models
  • Speech Models
  • Music & Vocal Models
  • Model Request
• Model Router
  • Getting Started
  • Integrating Router
  • Router Parameters
  • Supported Models

More

• Models comparsion
• Using Assistants & Threads

FAQ

• Can I use API in Python?
• Can I use API in NodeJS?
• Premium Models?
• Free Usage?
• How to Check API Status?
• My requests are cropped?
• OpenAI SDK doesn't work?

Glossary

• Concepts