Stability AI Image API by Stability AI

# Fix list: Stability AI Image API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/stability-ai-image, the October 2026 research run, assessed 1 October 2026. Grade E, 42.6 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 Stability AI Image 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: One bearer API key per account from the platform page, no scopes found (20). No least-privilege mode or spend cap found (0). Returns generated images only (10). No per-call log found (0). No security.txt, 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. Schema & documentation, 39 out of 100, up to 9.9 more on the total

Why it scored 39: No public OpenAPI spec found, and two likely paths on api.stability.ai return 404 (0). No llms.txt; platform.stability.ai/llms.txt returns the docs app shell (0). Endpoint pages describe each operation, but the docs are a JavaScript app our fetcher can't read (12). Multipart form inputs with enums for aspect ratio and output format (10). Examples per endpoint, error responses not checked (7). Dated release notes, same JavaScript app (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.

## 3. Agent ergonomics, 48 out of 100, up to 8.5 more on the total

Why it scored 48: `accept: image/*` returns raw bytes and `application/json` returns base64, so an agent can choose but never gets a URL (18). Format and aspect ratio controls (12). Error responses not checked in this run (8). No idempotency key, and some edit and upscale endpoints are async jobs to poll (5). The only official SDK is the legacy gRPC client from May 2024 (5).

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. Maintenance & community, 8 out of 100, up to 8.1 more on the total

Why it scored 8: The last image release in the notes, per the listing, is Style Transfer in April 2025, but Stability's own API notebooks on GitHub added SD 3.5 Flash on 31 July 2025. Either way it's more than 180 days ago (0). Newer work covers audio, with Stable Audio 3 examples added on 14 May 2026, not images (0). Public release notes and support, not tested (5). The official Python SDK is the gRPC client last released in May 2024 (3). Nothing current 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.

## 5. Reliability, 60 out of 100, up to 8 more on the total

Why it scored 60: Status page at status.stability.ai on Statuspage, with incident JSON (20). One incident in the last 90 days, rated major, elevated 500s on generation endpoints across the API Platform, Brand Studio and Stable Audio from 16:33 to 20:41 UTC on 14 September 2026, 4 hours 8 minutes (10). Limit of 150 requests every 10 seconds, per the listing's 30 September check (15). A 429 locks the caller out for 60 seconds, documented, but no Retry-After or backoff advice (10). No SLA (0). The endpoints agents call sit under `/v2beta` (5).

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.

## 6. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Fixed credit prices per call published at $0.01 a credit (20). 25 free credits on sign-up (20). 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.

## 7. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 40, provenance 86.

Why it scored 63: Closed API under terms that took effect on 30 September 2026. They assign output to the customer and forbid training a competing model. SD 3.5 weights are public under Stability's community licence, not an OSI licence (15). The privacy policy (effective 31 July 2025) says inputs and outputs may be used for training with an opt-out, and gives no retention period for API content (10). Dated notices for the July 2025 end of SVD and SD 1.6 and the August 2025 price rise (10). Processing in the US with controllers named per region, no subprocessor list (5).

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: stability.ai, registered 2019-11-06 (6 years) (11 of 15)
- 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.

- unchecked: the docs, pricing and release notes, which render only with JavaScript. platform.stability.ai/llms.txt returns the same app shell and two likely OpenAPI paths returned 404, so prices, limits, the free credits and error responses rest on the listing's 2026-09-30 research
- unchecked: whether the 25 sign-up credits need a card
- The date SD 3.5 Flash reached the API. Stability's notebooks added it on 31 July 2025, which we take as the newest image release we can date

## Weaknesses

- No new image model we could date since SD 3.5 Flash in July 2025
- A major incident on 14 September 2026 returned elevated 500s on generation endpoints for 4 hours 8 minutes
- Official Python SDK is the legacy gRPC client, last released in May 2024
- Docs, pricing and release notes are a single-page app with no llms.txt or OpenAPI spec
- No security.txt, no scoped keys, and API inputs and outputs may train models unless you opt out

## 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.

- Send `accept: image/*` to get bytes back, or `application/json` for base64
- Stay under 150 requests every 10 seconds. A 429 locks you out for 60 seconds
- Poll the result endpoint with the returned id for async edit and upscale calls
- Use Stable Image Core or SD 3.5 Flash for drafts, Ultra for finals
- Send multipart form data, not JSON

## What the review panel asked for

- Machine-readable docs
- Retry-After on 429
- publish prices as static text

## 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.