Your first image in five steps
Create an organization API key, submit a generation, and poll it to a finished asset — with copy-paste curl, Python, and TypeScript.
Three ways in
REST API
Generate, edit, transform, and train over plain HTTP.
MCP server
Drive the same tools from Claude, ChatGPT, Cursor, or n8n — one URL, nothing
to install.
Content verification
Check whether an image or video was made with Samsa. Free, no key needed.
What you can build
Image generation
Prompt to image, composed with your organization’s trained models and color
palettes.
Magic Edit
Edit an existing image from a prompt, with or without a mask.
Image operations
img2img, variations, resize, upscale, background removal, and vectorization.
Video generation
Video from a start frame, from text, or from text styled with your models.
Model training
Train style, object, person, and setting models from a handful of images.
Account & usage
Check a key, the credit balance it can spend, and your organization’s usage.
Before you build
Authentication
Organization keys, scopes, and the Bearer header every request needs.
Pricing
What each action costs in credits, and what happens when the pool runs out.
Rate limits
Per-key request rate, per-organization concurrency, and how to back off.
Errors
The error envelope, every code you can receive, and how to handle it.
Image inputs
How to supply source images — by
image_id, https URL, or base64.Changelog
New endpoints and MCP tools, newest first.
Every generation endpoint is asynchronous: a
POST returns 202 Accepted
with a job id, you poll the matching GET — or supply a webhook_url — and
a completed job carries presigned URLs to the finished assets.