Leonardo.Ai API by Leonardo.Ai (Canva)

# Fix list: Leonardo.Ai API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/leonardo-ai, the October 2026 research run, assessed 1 October 2026. Grade F, 37.8 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 Leonardo.Ai 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. Reliability, 30 out of 100, up to 14 more on the total

Why it scored 30: No status page. status.leonardo.ai failed TLS when the listing was researched and the limits guide links none (0). No readable incident history (5). Concurrency, queue and rate limits are defined and default numbers sit in the limits reference, 10 concurrent jobs per the listing's research (15). The limits guide says nothing about which status code comes back when a limit is hit or how to back off (0). No SLA found (0). The v2 generations endpoint is 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.

## 2. Payments & pricing, 0 out of 100, up to 12.5 more on the total

Why it scored 0: No x402, MPP or L402 (0). No per-image price list. Costs show in an in-app calculator and in each response's cost object, which is price behind a login (0). No API free tier documented (0). 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. Security & auth, 40 out of 100, up to 10.5 more on the total

Why it scored 40: Bearer API keys created in the web app, revocable, no scopes found (20). No read-only key, spend cap or least-privilege mode found (0). Returns generated images only (10). Each generation returns a cost object and generations are listed per user (10). No security.txt, bug bounty or certification found for Leonardo (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.

## 4. Schema & documentation, 45 out of 100, up to 8.9 more on the total

Why it scored 45: No public OpenAPI spec found (0). llms.txt for the docs (10). Guides describe each model, but we found no when-not-to-use guidance (8). The SDKs are typed with Zod schemas, and one `model` string on the v2 endpoint chooses among many shapes (10). Examples in the guides, no error catalogue found (7). v1 and v2 paths and a dated deprecations page, no full changelog (10).

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.

## 5. Agent ergonomics, 54 out of 100, up to 7.5 more on the total

Why it scored 54: Results come back as image URLs, and the hosted MCP server does image generation only (20). Pagination and output filters not checked in this run (5). Limit errors undocumented (8). No idempotency key. Webhook callbacks on the key avoid polling (6). Official TypeScript and Python SDKs (15).

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.

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

Why it scored 48: The last dated API change is the removal of Sora 2 on 9 July 2026, 84 days ago. The TypeScript SDK's last release, 4.21.3, was on 21 April 2026 (20). For models we look at churn and notice. Six removals or breaking changes since April 2026 with 8 to 28 days' notice and no stated policy (3). Public deprecations page and a contact form (6). Official TypeScript and Python SDKs, the TypeScript one five months old (12). The SDK publishes from GitHub Actions through npm trusted publishing (7).

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, 51 out of 100, up to 4.3 more on the total

Made of editorial 25, provenance 76.

Why it scored 51: Closed API under Leonardo's terms. Leonardo Interactive Pty Ltd is a Canva subsidiary (15). leonardo.ai returns 403 to our fetcher, so we couldn't read the privacy policy or retention statements in this run (0). Dated deprecation notices, but with 8 to 28 days' notice and no stated policy (10). No subprocessor list or data locations found (0).

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: leonardo.ai, registered 2019-01-08 (7 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 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.

- leonardo.ai returns 403 to our fetcher, so terms, privacy and pricing pages weren't read in this run.
- The default limit numbers sit on docs.leonardo.ai/reference/limits, which the fetch budget didn't let us reopen. The 10-job figure is from the listing's 2026-09-30 research.
- We couldn't date the newest third-party model additions, so the last API change is taken from the deprecations page.

## Weaknesses

- No per-image price list outside the logged-in calculator
- No status page and no security.txt
- Deprecation notice of 8 to 28 days with no stated policy
- No documented status code or backoff advice for limit errors
- TypeScript SDK last released on 21 April 2026

## 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 `POST /api/rest/v2/generations` with a `model` name such as `lucid-origin`
- Read the `cost` object in each response to track spend, prices aren't published
- Send `quality`, not `mode`. `mode` was retired on 2026-05-04
- Set a webhook callback URL on the key instead of polling long jobs
- Check the deprecations page before relying on a third-party model, removals follow the provider

## What the review panel asked for

- Public price table
- Document limit responses
- publish a per-image price table
- return a cost estimate before generating

## 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.