Skip to main content
Glama

MiniMax MCP Server by useapi.net (third-party)

Generate a video

minimax_create_video

Generate a video on hailuoai.video with Hailuo 3.0, 02 / 2.3, Hailuo 01, Veo 3.1 (incl. subject reference S2V) or Seedance 2.0 / Fast / Mini, from text, a first frame (fileID), an end frame, subject images (fileID2-14 on S2V) or omni references cited in the prompt as @Image1-9, @Video1-3, @Audio1-3 (Seedance, Hailuo-3.0). Hailuo 02 / 2.3 and Veo set size and length with options; Seedance and Hailuo-3.0 with resolution and duration. Uses the account's MiniMax credits (minimax_get_features). Waits up to ~50 s, then returns the videoId for minimax_get_video. POST /videos/create.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "minimax_create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
modelNoDefault T2V-01 for text, I2V-01 with a fileID. T2V-* need no image, I2V-* and S2V-* require fileID; 02, Veo-3.1, Seedance and Hailuo-3.0 take either.
fileIDNoThe first frame / main image (omni @Image1 on Seedance and Hailuo-3.0, the subject on S2V models): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
promptNoWhat happens in the video. Up to 2,000 characters (7,500 on Seedance, 7,000 on Hailuo-3.0, where it is required). Optional on image models; T2V-01-Director / I2V-01-Director take camera moves as [<movement>] in the prompt.
accountNoThe account to use; with a fileID the file's account is used: the account id from minimax_list_accounts. Omit to let the API pick one of your accounts.
fileID2NofileID2: an extra image reference (S2V subject image, or omni @Image2 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID3NofileID3: an extra image reference (S2V subject image, or omni @Image3 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID4NofileID4: an extra image reference (S2V subject image, or omni @Image4 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID5NofileID5: an extra image reference (S2V subject image, or omni @Image5 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID6NofileID6: an extra image reference (S2V subject image, or omni @Image6 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID7NofileID7: an extra image reference (S2V subject image, or omni @Image7 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID8NofileID8: an extra image reference (S2V subject image, or omni @Image8 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID9NofileID9: an extra image reference (S2V subject image, or omni @Image9 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
maxJobsNoOverride the account's maxJobs (generations at once) for this request, 1-10.
optionsNoSize and length for 02 (512p only image-to-video), T2V-2.3 / I2V-2.3 / I2V-2.3-Fast (768p or 1080p) and Veo-3.1* (veo-*). Not for Hailuo 01, Seedance or Hailuo-3.0.
durationNoSeconds, Seedance and Hailuo-3.0 only: 4-15 (default 5).
fileID10NofileID10: an extra image reference (S2V subject image, or omni @Image10 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID11NofileID11: an extra image reference (S2V subject image, or omni @Image11 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID12NofileID12: an extra image reference (S2V subject image, or omni @Image12 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID13NofileID13: an extra image reference (S2V subject image, or omni @Image13 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
fileID14NofileID14: an extra image reference (S2V subject image, or omni @Image14 on Seedance and Hailuo-3.0, which stop at fileID9); fill slots in order after fileID: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
replyRefNoOptional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters.
replyUrlNoOptional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters.
resolutionNoSeedance and Hailuo-3.0 only: 480 / 720 (Seedance, default 720), 1080 / 4K (Seedance-2.0 only), 768 / 1440 = 2K (Hailuo-3.0, default 1440).
aspectRatioNoVeo-3.1*: 16:9 (default) or 9:16. Seedance and Hailuo-3.0: Auto (match the references), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Other models take the image's ratio.
audioFileID1NoaudioFileID1: an MP3 / WAV omni reference cited as @Audio1 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
audioFileID2NoaudioFileID2: an MP3 / WAV omni reference cited as @Audio2 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
audioFileID3NoaudioFileID3: an MP3 / WAV omni reference cited as @Audio3 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
videoFileID1NovideoFileID1: an MP4 omni reference cited as @Video1 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
videoFileID2NovideoFileID2: an MP4 omni reference cited as @Video2 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
videoFileID3NovideoFileID3: an MP4 omni reference cited as @Video3 (Seedance and Hailuo-3.0; 2-15 s each, 15 s in all; not with end_frame_fileID; fill in order): a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
end_frame_fileIDNoThe last frame (02 at 768p / 1080p, Veo-3.1, Veo-3.1-Fast, Seedance, Hailuo-3.0); not the same file as fileID, not with omni references: a fileID from minimax_upload_file, minimax_list_files, minimax_list_characters or a completed image (minimax_get_image), on the same account.
promptOptimizationNoLet MiniMax rewrite the prompt (default false).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only, non-idempotent, open-world write, and the description adds real context beyond that: it consumes the account's MiniMax credits, blocks up to ~50 s by default (with the wait=false escape hatch implied by the schema), and returns a videoId rather than a rendered file. It stops short of describing failure/timeout behavior or cost magnitude, which matters for a credit-spending generation call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every sentence conveys operational information that is hard to assemble from 33 scattered field descriptions. The first sentence is very dense with model and slot enumerations, making it slower to parse than necessary, but there is no filler or promotional wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 33-parameter, no-output-schema, credit-consuming generation tool, the description covers the essential pieces: input modes, model selection, parameter-family rules, credit usage, blocking behavior, return value, and the retrieval tool. Remaining gaps are secondary details like failure handling and relative model quality/cost, which the agent could learn from minimax_get_features.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each of the 33 parameters already documents its model applicability, enum meaning, and file-resolution chain, so the schema carries nearly all semantic weight and baseline 3 applies. The description adds a useful cross-cutting summary of the model-to-parameter mapping (options vs resolution/duration, @Image/@Video/@Audio citation limits) but repeats rather than extends the per-field text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ('Generate a video') and immediately enumerates the supported model families (Hailuo 3.0, 02/2.3, Hailuo 01, Veo 3.1, Seedance 2.0) and input modes (text, first frame, end frame, subject images, omni references). It also names the concrete endpoint and the follow-up retrieval tool, so an agent can distinguish it from create_image/create_music/create_template_video without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly states which models accept which inputs (T2V needs no image, I2V/S2V require fileID, 02/Veo/Seedance/Hailuo-3.0 take either) and which parameter family sets size/length per model ('options' for 02/2.3/Veo, 'resolution'/'duration' for Seedance and Hailuo-3.0). It points to minimax_get_features for credits and minimax_get_video for retrieval, but gives no explicit exclusion such as cost-based or concurrency-based when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources