Get Started

Overview

Overview

Pureframe is a video intelligence API. Upload your footage and Pureframe indexes every frame and spoken word — then find any moment with a natural language query or a reference image.

What you can build

Video search for apps

Let users search hours of footage with a simple text query — no scrubbing required.

Agent vision

Give Claude, GPT-4o, or any LLM the ability to see and search your video library via MCP or function calling.

Content moderation

Locate specific scenes, objects, or dialogue across a large library automatically.

Training data curation

Extract relevant moments that match a description — at scale.

How it works

1

Upload

Send a video file to POST /v1/upload with a collection_id. Pureframe returns a job_id immediately — processing runs in the background.

2

Index

Pureframe extracts frames, generates visual embeddings, and transcribes speech. The job moves through queued → processing → done. You can poll GET /v1/jobs/{job_id} for live progress.

4

Use the clips

Each result includes thumbnail_base64 — a base64-encoded JPEG that vision-capable models can consume directly without fetching a URL.

Base URL

https://api.pureframe.ai

All endpoints are versioned under /v1.

Response envelope

Every API response shares the same wrapper:

1{
2  "data": { ... },
3  "meta": {
4    "request_id": "req_abc123",
5    "took_ms": 42,
6    "total": 10,
7    "page": 1,
8    "per_page": 10
9  }
10}

Errors return a non-2xx status with a machine-readable code:

1{
2  "detail": {
3    "code": "COLLECTION_NOT_FOUND",
4    "message": "Collection not found"
5  }
6}

See Error Codes for the full list.

Jump in

Quickstart

Upload a video and run your first search in under 5 minutes.

API Reference

Complete documentation for every endpoint.

Agent Vision

Connect Pureframe to any AI agent via MCP or function calling.

Pricing

Free tier, Pro plan, and enterprise options.