Creatomate vs Photoroom API

Creatomate

A hosted MCP server with eight tools, OAuth with PKCE and per-project connections sits beside a small REST API whose errors carry a hint and a documentation link, and dry_run validates a render at no cost. No status page, changelog, OpenAPI file or security contact was found, and the terms and privacy policy date from June 2022.

Photoroom API

A call costs $0.02 for background removal or $0.10 for any combination of edits, and a sandbox key gives 1,000 free watermarked calls a month without a card. No status page or official SDK was found, and Photoroom's privacy policy and security page disagree on whether API images train its models.

Creatomate

1. Send "dry_run": true to POST /v2/renders before a paid render. It returns valid, errors, warnings and the effective source
2. Read warnings on every render response. A modification keyed to an unknown element or property name is ignored without an error
3. Keep under 30 requests per 10 seconds across the whole account, and wait for Retry-After on a 429
4. Download each file when the webhook fires. Renders, their URLs and their status records are deleted after 30 days
5. Use render_scale 0.5 for draft videos, about a quarter of the credits, and remember MCP create_render spends credits without a confirmation step from the server

Photoroom API

1. Send the key in the x-api-key header. Prefix it with sandbox_ while testing, because calls with the plain key consume paid images
2. Save the response body as a file. A 200 returns image bytes, PNG by default, and any other status returns JSON with error.message or detail
3. Send model selectors such as pr-ai-shadows-model-version: 2026-04-15 as HTTP headers, not form fields. They are not in the OpenAPI file
4. Stay under 60 images a minute. On 429 back off with an exponential delay, and set a client timeout of at least 60 seconds for AI edits
5. Use POST /v2/edit with imageFile for local files and GET /v2/edit with imageUrl for hosted ones. Each call takes one image