Recraft API by Recraft

# Fix list: Recraft API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/recraft, the October 2026 research run, assessed 1 October 2026. Grade D, 53 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Recraft API: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: Bearer API tokens from the profile page, several tokens sharing one balance, no scopes. The hosted MCP server uses OAuth 2.0 (20). No least-privilege mode or spend cap found (0). Returns generated images only (10). No per-call log found (0). security.txt expired on 11 November 2025, and no bug bounty or certification found (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Per-image and per-operation prices published without a login (20). No free API allowance. The web Free plan's credits work through the hosted MCP with no card, but free-plan images belong to Recraft and are public (10). Browser sign-up (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 3. Agent ergonomics, 62 out of 100, up to 6.2 more on the total

Why it scored 62: `response_format` lets an agent choose a URL, base64 or multipart, so the payload can stay small (25). Size, count and format controls (15). Errors not documented (5). No idempotency key, and no MCP annotations found (5). Default model set, few required fields. No Recraft SDK, but the OpenAI SDKs work with a new base URL (12).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 4. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Instatus page (status.recraft.ai redirects to recraft.instatus.com) with Website, App and API components (20). No notices in August or September 2026 and 100 per cent shown for the API. The page we read didn't cover July, so two of the three months are seen clean (25). Limits of 100 images a minute and 5 requests a second per user (15). No 429 or backoff guidance found (0). No SLA (0). GA (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Schema & documentation, 64 out of 100, up to 5.9 more on the total

Why it scored 64: A Swagger UI at external.api.recraft.ai/doc, but no spec file we could fetch (15). llms.txt for the docs (10). The docs say which endpoint returns vectors and which model to use for drafts, raster or SVG (13). Typed inputs with enums for model, style and response format (12). Examples in the docs, no error reference found (7). Model release months on the getting started page, no changelog (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Maintenance & community, 48 out of 100, up to 4.6 more on the total

Why it scored 48: V4.1 Flash released in September 2026, within 30 days (30). For models we look at churn and notice. Every model back to V2 (February 2024) is still served, so nothing has needed notice, but no policy exists for when it does (15). No public changelog, support not tested (3). No official SDK, the old stdio MCP repo is archived and the hosted server isn't in the MCP registry (0). No packages to assess (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 61 out of 100, up to 3.4 more on the total

Made of editorial 45, provenance 77.

Why it scored 61: Closed API with published terms and a commercial-rights page that bars training on outputs (15). The privacy policy (12 March 2026) says Recraft won't train on AI inputs or outputs without affirmative authorisation, yet also describes an opt-out in account settings, and gives no retention periods. Generated images sit at signed public URLs for about 24 hours (15). No deprecation policy or dated notices found (0). A subprocessor page at recraft.ai/subprocessors lists outside AI model providers, but data locations are only 'countries outside your home country' (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: recraft.ai, registered 2022-06-27 (4 years) (7 of 15)
- Changelog: not found (0 of 10)
- security.txt: published but past its Expires date (5 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- The Instatus page we read didn't include July 2026, so the first month of the 90-day window is unseen.
- The getting started page gives release months, not days, so lastRelease stays empty.
- The fetch budget ran out before we could re-read pricing, the appendix and the MCP page. Those lines rest on the listing's 2026-09-30 research.
- The privacy policy says no training without affirmative authorisation but also mentions an opt-out, so the default isn't clear.

## Weaknesses

- No changelog and no error reference
- security.txt expired on 2025-11-11, no bug bounty or certification found
- Result URLs are public to anyone holding the link for about 24 hours
- No free API allowance, and the hosted MCP bills Studio credits, not API units
- No 429 or backoff guidance

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Use `/v1/images/generations/vector` when the task must return SVG, so the server rejects raster models
- Ask for `b64_json` or `multipart` if you can't fetch the URL within a day
- Name `recraftv4_1_flash` for drafts at $0.007. The default `recraftv4_1` costs $0.035
- Stay under 100 images a minute and 5 requests a second per user
- Point the OpenAI SDK at `https://external.api.recraft.ai/v1`, but expect some parameters to be ignored

## What the review panel asked for

- Error reference
- Private result URLs
- one meter across API and MCP

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.