Magic Hour

Magic Hour is an AI media generation platform for video, image and audio, exposed as a public REST API. The contract is an OpenAPI 3.0 document of 33 paths and 36 operations served from api.magichour.ai with bearer authentication, covering generators for headshots, clothes changing, face editing, GIFs, image editing and upscaling, plus video and audio synthesis. Operations are priced in credits and the documentation states the credit cost per call. Magic Hour publishes two llms.txt files — one on the marketing site and a different one on the docs host — plus a 653KB llms-full.txt, and documents an HMAC-SHA256 signed webhook surface with a full event-type reference.

Magic Hour publishes 1 API on the APIs.io network. Tagged areas include AI, Media Generation, Video, Image, and Audio.

23.1/100 emerging ▬ flat Agent 21/100 agent aware Full breakdown ↓
scored 2026-08-25 · rubric v0.14.0
1 APIs
AIMedia GenerationVideoImageAudioGenerative AIWebhooks

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-25 · rubric v0.14.0
Composite quality — 23.1/100 · emerging
Contract Quality 14.0 / 25
Developer Ergonomics 1.9 / 20
Access Clarity 0.0 / 20
Operational Transparency 0.0 / 13
Contract Governance 0.0 / 12
Discoverability 7.2 / 10
Agent readiness — 21/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 7 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Delegated User Identity 0 / 6
Protected Resource Metadata 0 / 5
Registration Without a Human 0 / 6
Agentic Commerce Surface 0 / 5
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/magichour: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Magic Hour API

AI generation of video, image and audio — headshots, clothes changer, face editor, GIF generator, image editor and upscaler among 36 operations. Bearer auth, credit-priced.

Resources

Get Started 1

Portal, sign-up, and the first successful call

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Company 1

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: magichour
name: Magic Hour
description: Magic Hour is an AI media generation platform for video, image and audio, exposed as a public REST API. The contract
  is an OpenAPI 3.0 document of 33 paths and 36 operations served from api.magichour.ai with bearer authentication, covering
  generators for headshots, clothes changing, face editing, GIFs, image editing and upscaling, plus video and audio synthesis.
  Operations are priced in credits and the documentation states the credit cost per call. Magic Hour publishes two llms.txt
  files — one on the marketing site and a different one on the docs host — plus a 653KB llms-full.txt, and documents an HMAC-SHA256
  signed webhook surface with a full event-type reference.
type: Index
url: https://raw.githubusercontent.com/api-evangelist/magichour/refs/heads/main/apis.yml
created: '2026-08-22'
modified: '2026-08-22'
specificationVersion: '0.23'
tags:
- AI
- Media Generation
- Video
- Image
- Audio
- Generative AI
- Webhooks
tags_raw:
- ai video
- image generation
- audio
- generative ai
apis:
- aid: magichour:magichour-api
  name: Magic Hour API
  description: AI generation of video, image and audio — headshots, clothes changer, face editor, GIF generator, image editor
    and upscaler among 36 operations. Bearer auth, credit-priced.
  humanURL: https://docs.magichour.ai
  baseURL: https://api.magichour.ai
  tags:
  - AI
  - Media Generation
  - Video
  properties:
  - type: OpenAPI
    url: openapi/magichour-api-openapi.yml
  - type: Documentation
    url: https://docs.magichour.ai
  - type: APIReference
    url: https://docs.magichour.ai/api-reference/openapi.json
  - type: Authentication
    url: https://docs.magichour.ai/get-started/authentication
  - type: GettingStarted
    url: https://docs.magichour.ai/get-started/quick-start
  - type: Webhooks
    url: https://docs.magichour.ai/integration/webhook/overview
common:
- type: LLMsTxt
  url: llms/magichour-llms.txt
- type: Website
  url: https://magichour.ai
- type: DeveloperPortal
  url: https://docs.magichour.ai
maintainers:
- FN: Magic Hour
  email: runbo@magichour.ai
  url: https://magichour.ai
x-provenance:
  added: '2026-08-22'
  method: searched
  source: https://docs.magichour.ai/llms.txt
  note: 'Submitted via apis.io/add on 2026-08-22 from runbo@magichour.ai and auto-published by the gate at rating 15. THE
    SUBMITTED APIs.json URL IS WRONG: https://docs.magichour.ai/apis.json returns 404, and an invented control path also 404s
    with a different body size, so the 404 is real rather than a catch-all. A bad pointer in the submission, not an absent
    surface. Everything here came from the provider''s own llms.txt, which names the specification at /api-reference/openapi.json.
    That was fetched (501KB, OpenAPI 3.0.2) and is kept pristine under openapi/_original/. Note the spec declares zero component
    schemas despite 36 operations, so request and response shapes are inline rather than reusable. The API was probed: POST
    api.magichour.ai/v1/ai-headshot-generator returned 401 JSON, which is correct gating on a live host. Two DIFFERENT llms.txt
    files exist, one on magichour.ai and one on docs.magichour.ai. Both are kept; the docs one is the richer and is what this
    profile was built from.'

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This provider
curl "https://apis.io/api/v1/providers/magichour"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/magichour/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/magichour/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.