Kling AI API by Kling AI (Kuaishou)

# Fix list: Kling AI API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/kling, the October 2026 research run, assessed 1 October 2026. Grade F, 22 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 Kling 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, 15 out of 100, up to 17 more on the total

Why it scored 15: No official status page found, only third-party monitors, and neither status.kling.ai nor status.klingai.com resolves (0). No incident history to read (5). Kling's developer docs render only with JavaScript, so we couldn't read rate limits or concurrency. Third parties report 5 concurrent tasks on trial packages and 20 on standard ones, which we didn't count (0). No 429 or retry guidance we could read (0). No SLA found (0). Kling 3.0 and 3.0 Omni are listed in kling.ai/llms.txt as current models with no preview label (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. Security & auth, 20 out of 100, up to 14 more on the total

Why it scored 20: Model reading of the checklist (credential, training, retention, operator visibility, programme). An AccessKey and SecretKey pair signs a short-lived JWT for each session, which keeps the secret off the wire, but we found no scopes and the secret key reaches everything (20). The Terms of Service, updated 21 April 2026, let Kling use Input to create, test, improve and train its models, and you can revoke that by email to support@kling.ai. They don't carve out API users, and the separate API paid-service terms render only with JavaScript, so we treat training as on by default (0). Data is kept as long as necessary for its purposes, with no period for API outputs (0). No audit log or per-call view found (0). No security.txt, 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.

## 3. Schema & documentation, 15 out of 100, up to 13.8 more on the total

Why it scored 15: No official OpenAPI. An independent profile on GitHub models the endpoints and says its schemas need checking against the live docs (0). kling.ai/llms.txt lists model IDs and per-second prices, but its links lead to pages that don't render without JavaScript, so half (5). llms.txt says what each model family is for, nothing more we could read (5). We couldn't read the parameter reference, so no typed inputs counted (0). No examples or error codes we could read (0). Versioned model IDs from kling-v1 to kling-v3, but no public changelog (5).

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.

## 4. Agent ergonomics, 27 out of 100, up to 11.9 more on the total

Why it scored 27: Create calls return a task id to poll, per the request flow in llms.txt and the listing's checks. A third-party profile describes a `callback_url`, which we couldn't confirm on an official page (15). Mode (std or pro) and duration set output size, and we couldn't confirm a task list (10). No error reference we could read (0). No idempotency key or retry guidance found (0). No official SDK, and every call needs a JWT you sign yourself from an AccessKey and SecretKey (2).

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. 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 prices for every current model are published in kling.ai/llms.txt without a login, $0.084 to $0.42 a second for Kling 3.0 (20). No free API tier, and consumer credits don't work on the API (0). A person signs up and buys a prepaid resource package (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.

## 6. Maintenance & community, 24 out of 100, up to 6.7 more on the total

Why it scored 24: Model reading. Kling 3.0 and 3.0 Omni came in February 2026. Third-party coverage of Kling's launch note puts Kling 3.0 Turbo on the API on 17 June 2026, 106 days ago, and Kling 4.0 announced on 28 September isn't on the API yet (10). Models from kling-v1 onward stay callable. No deprecation policy found, and Turbo and later models need newly generated keys, per the same launch note (10). No public changelog, support by email (4). No official SDK (0). Nothing to assess for package health (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, 46 out of 100, up to 4.7 more on the total

Made of editorial 30, provenance 62.

Why it scored 46: Closed models. The Terms of Service (updated 21 April 2026, Singapore law, Kling AI Pte. Ltd. at One Raffles Place) are readable and say what Kling may do with your content, but the separate API paid-service terms render only with JavaScript (12 of 15). The privacy policy says data is stored on servers in Singapore and kept as long as necessary, and the terms add the training clause with an email opt-out. No DPA and no retention periods found (8 of 30). No deprecation policy or dated notices (0). Singapore storage and categories of service providers are disclosed, no named subprocessors (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: klingai.com, registered 2024-03-26 (2 years) (7 of 15)
- Status page: not found (0 of 10)
- Changelog: 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.

- unchecked: everything in the JavaScript-only developer docs, including rate limits, error codes, callbacks, resource package sizes and expiry, and the Kling Skills page. llms.txt, llms-full.txt and three docs pages were tried again on 2 October
- unchecked: whether the API paid-service terms override the Terms of Service clause that allows training on Input
- The official model ID and price for Kling 3.0 Turbo, and the exact date it reached the API. llms.txt still lists only 2.5 Turbo and was last priced on 29 May 2026, so we have only third-party summaries of the launch note
- When Kling 4.0 reaches the developer API

## Weaknesses

- Developer docs, API terms and pricing render only with JavaScript
- No official SDK, OpenAPI, status page or changelog
- Auth needs a self-signed JWT, and Turbo and later models need newly generated keys
- Prepaid resource packages, separate from consumer credits
- The Terms of Service let Kling train on your Input unless you revoke it by email

## 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.

- Sign a JWT (HS256) with `iss` set to your AccessKey and a 30 minute `exp`, then send it as a bearer token
- Generate a new key pair if you need Kling 3.0 Turbo. Older keys don't reach it
- Create with POST /v1/videos/text2video or /v1/videos/image2video, then poll the task id until it succeeds
- Take model IDs and prices from kling.ai/llms.txt. The HTML docs need JavaScript
- Email support@kling.ai to revoke training use of your Input. The terms don't exempt API calls

## What the review panel asked for

- Markdown or OpenAPI reference
- Official SDK
- publish package expiry in plain 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.