Runway API by Runway

# Fix list: Runway API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/runway, the October 2026 research run, assessed 1 October 2026. Grade C, 61.1 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 Runway 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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Per-second credit prices for every model are published at $0.01 a credit without a login, 12 credits a second for Gen-4.5 (20). No free generation credits, $10 minimum first purchase (0). A person signs up in the developer portal and buys credits (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.

## 2. Security & auth, 51 out of 100, up to 8.6 more on the total

Why it scored 51: Model reading of the checklist (credential, training, retention, operator visibility, programme). One bearer key per project from the developer portal. The hosted MCP server uses OAuth. No permission scopes found on keys (20). Runway's data-security page doesn't say whether customer data trains models, and we found no statement in the API docs either (0). Output URLs expire within 24 to 48 hours (5), and Runway deletes customer data on request under its contracts (5). No input retention period found (0). Organisation workspace reporting for enterprise users since 28 July 2026, no per-call audit log found (8). No security.txt and no public disclosure policy (0). A private, invitation-only bug bounty (3). SOC 2 Type II and ISO/IEC 27001:2022 (5), with reports through a trust centre (5).

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.

## 3. Reliability, 75 out of 100, up to 5 more on the total

Why it scored 75: Atlassian Statuspage at status.runwayml.com with a Public API component and RSS history back to April 2026 (20). Three incidents in the last 90 days, all on generation models and none filed against the API. Aleph 2.0 generations were delayed for 23 minutes on 8 July, an unnamed fault ran 54 minutes on 10 July and Aleph 2 generations were degraded for 2 hours 21 minutes on 29 September. One model degraded rather than the API down, so minor only (20). The tiers page publishes per-model concurrency and a rolling 24-hour generation cap for each spend tier (15). Over the concurrency limit, tasks queue as THROTTLED instead of failing, and only the daily cap returns 429. Failure codes say which failures not to retry, but we found no Retry-After or backoff guidance (10). No SLA published for self-serve tiers (0). The API and its models are generally available (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.

## 4. Agent ergonomics, 75 out of 100, up to 4.1 more on the total

Why it scored 75: Tasks are small JSON objects with output URLs, and the official SDKs include a wait-for-output helper, so an agent needn't write a polling loop (25). Ratio, duration and model choice set output size. No task list endpoint found (10). Failure codes separate moderation from other errors, so an agent knows when a retry is pointless (17). No idempotency key. The docs say not to retry SAFETY failures unchanged (10). Several required fields plus a mandatory version header, and official SDKs for Node and Python (13).

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.

## 5. Transparency & trust, 57 out of 100, up to 3.8 more on the total

Made of editorial 28, provenance 86.

Why it scored 57: Closed models under Runway's terms of use, SDKs Apache 2.0. We didn't read the terms for output rights in this run (8). The data-security page describes a retention framework and deletion on request but gives no periods and no training statement (5). The changelog dates removals, but the July removals came without advance notice (5). A customer subprocessor list is published. Data centres aren't named by country (10).

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: runwayml.com, registered 2018-03-13 (8 years) (11 of 15)
- security.txt: not found (0 of 10)

## 6. Maintenance & community, 62 out of 100, up to 3.3 more on the total

Why it scored 62: Model reading. Latest changelog entry on 30 September 2026, and 23 dated entries since early July (30). Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 30 July 2026 with no earlier notice in the public changelog (0). Busy dated changelog and a support desk (12). Official SDKs on npm and PyPI, the newest release on 23 September 2026 (15). SDK repositories are public on GitHub. We didn't check their CI in this run (5).

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. Schema & documentation, 93 out of 100, up to 1.1 more on the total

Why it scored 93: OpenAPI 3.1 at docs.dev.runwayml.com/openapi.json (25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Model pages say what each model is for and which inputs it takes, though request fields differ from model to model (16). Typed fields with fixed ratios and duration ranges per model (13). Examples in curl, Node and Python, and failure codes such as SAFETY.* documented with what they mean (14). A dated X-Runway-Version header and a dated changelog with 23 entries between July and September 2026 (15).

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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-07-30, Gen-3 Alpha Turbo (`gen3a_turbo`) and Gen-4 Aleph (`gen4_aleph`) were removed and calls with those IDs began to fail. The changelog announced it the same day and shows no earlier notice. Runway may have emailed customers, so we deduct at the low end (https://docs.dev.runwayml.com/api-details/api_changelog/)

## 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.

- Whether Runway emailed API customers before removing gen3a_turbo and gen4_aleph on 30 July 2026
- Whether Runway trains on API inputs or outputs. The data-security page doesn't say
- What Runway's terms say about output ownership for API customers

## Weaknesses

- Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 2026-07-30 with no prior notice in the changelog
- Prepaid credits only, $10 minimum, no free generation credits
- No idempotency key and no Retry-After guidance found
- Request fields differ per model, so bodies aren't portable between models
- No security.txt, and no training statement for customer data found

## 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 `X-Runway-Version: 2024-11-06` on every request or it fails
- Use the SDK's wait-for-output helper or poll GET /v1/tasks/{id} until SUCCEEDED or FAILED
- Don't retry a SAFETY.* failure unchanged. It's moderation, not an outage
- Take model IDs from the models page, not memory. Two were removed without notice on 2026-07-30
- Copy outputs to your own storage. URLs expire within 24 to 48 hours

## What the review panel asked for

- Advance notice on removals
- Idempotency key
- Document failed-task refunds

## 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.