Pureframe AI API Documentation

Pureframe AI is a video search API. Upload your footage, wait for processing to finish, and retrieve relevant timestamped segments with a text query, a reference image, or both.

How it works

Upload

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

Index

Pureframe AI prepares visual, transcript, and on-screen text signals. The job moves through queued → processing → done. Poll GET /v1/jobs/{job_id} for progress.

Send a text query, image file, or image URL to POST /v1/search. Results contain ranked segments, timestamps, playback URLs, thumbnails, and matching transcript text when available.

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:

{
  "data": { ... },
  "meta": {
    "request_id": "req_abc123",
    "took_ms": 42,
    "total": 10,
    "page": 1,
    "per_page": 10
  }
}

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

{
  "detail": {
    "code": "COLLECTION_NOT_FOUND",
    "message": "Collection not found"
  }
}

See Errors for the full list.

Jump in

Quickstart

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

Key Concepts

The mental model: collections, jobs, modalities, credits.

Search

Text, image, and transcript search, and how they combine.

Agent Vision

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

Get Started

Search

Video Processing

Agents

Production

Resources

Overview

How it works

Base URL

Response envelope

Jump in

Quickstart

Key Concepts

Search

Agent Vision

​How it works

​Base URL

​Response envelope

​Jump in

Quickstart

Key Concepts

Search

Agent Vision

How it works

Base URL

Response envelope

Jump in