gunnigunni
Get Started
Documentation

Getting Started

Gunni is a unified API for AI media generation. One key, one endpoint, access to 17+ models across Google, Fal, and OpenAI.

Generate images, edit photos with natural language, create video from stills or text, synthesize speech, upscale, remove backgrounds, and more. Use Gunni from the CLI, through MCP in Claude Desktop or Cursor, or via the HTTP API from any language.

1. Create an account

Sign up at gunni.ai/signup. Every account gets 10 free credits on creation. No credit card required.

2. Get your API key

After signing in, go to gunni.ai/keys to create an API key. Keep it secret. You can create multiple keys for different projects or environments.

3. Choose your integration

CLI
Run commands in your terminal. No code required.
MCP
Use from Claude Desktop, Cursor, or Claude Code via Model Context Protocol.
HTTP API
Call the MCP API directly from any language using HTTP.
Models
Browse all 17+ models: image, video, audio, upscale, and more.

Quick example

Generate an image from the CLI in one line:

npx gunni image "a fox in watercolor style" -o output.png

Or from any MCP-compatible client (Claude Desktop, Cursor, Claude Code), ask naturally:

"Generate a watercolor painting of a fox"

The Gunni MCP tools handle model selection, routing, and file delivery automatically.