Visgate Documentation
Unified vision AI gateway. One API for image and video generation across Fal, Replicate, Runway, and RunPod.
What is Visgate?
Visgate is a unified multimodal AI gateway that routes image and video generation requests across multiple providers — Fal, Replicate, Runway, and RunPod — through a single API. It manages provider keys, caching, usage tracking, and billing so you can focus on building.
Quick Start
Generate your first image in under a minute with Python or JavaScript.
Authentication
Learn how to authenticate with API keys, server proxy, or session tokens.
Client Setup
Install and configure the Python or JavaScript SDK.
API Reference
Full reference for all endpoints: generate, images, videos, models, usage.
How it Works
One request enters Visgate. The synced catalog provides price and metadata. Routing and caching choose the optimal path. Providers run the job. Request, output, and latency logs return to your console.
Rendering diagram...
SDKs
| SDK | Package | Install |
|---|---|---|
| Python | visgate-sdk | pip install visgate-sdk |
| JavaScript | @visgate_ai/client | npm install @visgate_ai/client |
| Server Proxy | @visgate_ai/server-proxy | npm install @visgate_ai/server-proxy |
Features
- Multi-provider routing — Fal, Replicate, Runway, and RunPod behind one API
- Managed and BYOK modes — use Visgate-managed keys or bring your own
- Intelligent caching — exact and semantic cache matching to reduce costs
- Usage tracking — per-request cost, latency, and provider logs
- Async video generation — submit long-running jobs and poll for results