MiniMax Video API by MiniMax

# Fix list: MiniMax Video API

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/minimax-video, the October 2026 research run, assessed 1 October 2026. Grade C, 60.3 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 MiniMax Video 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, 38 out of 100, up to 10.9 more on the total

Why it scored 38: Model reading of the checklist (credential, training, retention, operator visibility, programme). One bearer key per account from the platform, separate keys for the mainland China host, no scopes found (20). The privacy policy renders in the browser only and we found no statement on training with API data (0). Tasks stay queryable for 7 days (5) and a DELETE call removes a task (5). We found no input retention period (0). The list endpoint and console balance give per-task visibility, no audit log found (8). 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.

## 2. 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 H3 and H3-Max are published without a login, $0.08 a second at 768P and $0.13 at 2K for H3 (20). No free tier published (0). A person signs up and tops up a balance before the first call (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. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Atlassian Statuspage at status.minimax.io with a Video Generation component, readable through its RSS feed (20). The feed reaches back to 13 September 2026 and holds 24 incidents, all on the LLM or text-to-speech components and mostly resolved within 5 to 15 minutes. None touched video. We couldn't read the earlier part of the 90 days, so minor only on what we saw (20). Video packages publish 20 to 50 requests a minute, pay-as-you-go limits aren't published (10). The OpenAPI file documents 429 for rate limits, with no Retry-After or backoff guidance found. Failed and moderated jobs aren't charged on packages (10). No SLA found (0). H3 carries 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.

## 4. Maintenance & community, 47 out of 100, up to 4.6 more on the total

Why it scored 47: Model reading. MiniMax H3 shipped on 31 July 2026, 62 days ago, and the listing records H3 Max on 21 August (20). Hailuo 2.3 and 02 stay callable on V1 as legacy after H3 arrived. No deprecation policy or dated retirements found (10). A dated release page and a support channel through the platform (12). No official SDK for video. The official MCP server's last README update, on 2 July 2025, added Hailuo-02, and it doesn't know H3 (0). The MCP repository is MIT with GitHub Actions workflows, 20 open issues and 18 open pull requests (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.

## 5. Agent ergonomics, 76 out of 100, up to 3.9 more on the total

Why it scored 76: Task objects are small and carry a download URL, and `callback_url` removes polling (25). Resolution, ratio and duration control output size, and GET /v2/query/video_generation lists tasks with pagination and filters (20). Typed errors with a request id, 402 for an empty balance and 422 for blocked content, which an agent can act on (18). No idempotency key found. Failed and moderated jobs aren't charged on packages and tasks can be cancelled with DELETE (10). Four required fields on create and no official SDK, only the MCP packages (3).

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. Transparency & trust, 58 out of 100, up to 3.7 more on the total

Made of editorial 30, provenance 86.

Why it scored 58: Closed API under the platform terms. H3 weights are published on Hugging Face under the MiniMax H3 Community License, which isn't an OSI licence (20). The privacy policy wouldn't render for us and we found no training statement (0). Task retention of 7 days is stated (5). No DPA read (0). Legacy models are labelled but no deprecation policy or dates (5). The contracting entity is Nanonoble Pte. Ltd. in Singapore. 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: minimax.io, registered 2021-03-27 (5 years) (11 of 15)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 96 out of 100, up to 0.7 more on the total

Why it scored 96: OpenAPI 3.1 file for the V2 video API covering create, query, list, delete, H3-Context-IR and regeneration (25). llms.txt on the platform docs (10). Long descriptions on every endpoint and field, including which references each model accepts and how many (17). Required fields and enums for model, resolution and ratio, a 4 to 15 second duration range, typed content items. The duration enum doesn't say H3-Max starts at 5 (14). Examples for text, image, reference and regeneration requests, and documented 400, 401, 402, 422, 429 and 500 responses with typed error bodies (15). Versioned V1 and V2 paths and a dated model release page (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.

## 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 MiniMax uses API inputs or outputs for training. The privacy policy didn't render for us
- Incident history on the Video Generation component before 13 September 2026
- The H3 Max release date, recorded in the listing as 21 August 2026 but not on the model release page

## Weaknesses

- No statement found on whether API inputs train models, and the privacy policy needs a browser
- No free tier, no SLA and no security.txt
- Pay-as-you-go rate limits aren't published
- Video packages from $1,000 cover Hailuo only, so H3 is pay as you go
- No official SDK, and the MCP server's video tool documents only Hailuo models

## 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 /v2/video_generation for H3 and poll GET /v2/query/video_generation/{task_id}. Tasks stay queryable for 7 days
- Set `ratio` for text-to-video. `adaptive` isn't allowed there
- Pass `callback_url` to skip polling. Your endpoint must echo the `challenge` within 3 seconds
- A 402 means the balance is empty and a 422 means moderation blocked the content. Don't retry either unchanged

## What the review panel asked for

- Publish pay-as-you-go limits
- Update MCP for H3
- publish reference image and video surcharges

## 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.