MiniMax (Hailuo) Commands & Prompt Reference

24 commands & parameters · 3 categories · Source: MiniMax Platform API Reference

MiniMax splits its surface in two: video generation (Hailuo) takes a multimodal content array where each item declares a type - text, image_url, video_url, or audio_url - alongside resolution, duration, and ratio; the chat API is OpenAI-compatible and adds its own thinking and reasoning_split controls on top of the familiar sampling fields. This page lists both from the official API reference.

The video endpoint is asynchronous: a successful call returns a task_id and you poll the query endpoint, or set callback_url to be notified. Every video scenario must include at least one text content item - the other content types are references layered on top of it.

All Commands

Video Generation Parameters (6)

Command / SyntaxWhat it doesNotes
modelModel nameCurrently available: MiniMax-H3.
contentArray of multimodal input describing the information used to generate the videoEach element is distinguished by type (text / image_url / video_url / audio_url) and can be labeled with a role. Every request must include one non-empty text item (the prompt is...
resolutionVideo resolutionCurrently available: 768P, 2K.
durationDuration of the generated video in secondsRequired, integer. Available values: 4-15.
ratioAspect ratio of the generated videoDefaults to adaptive (the most suitable ratio is chosen automatically based on the input; the actual ratio can be read from the ratio field of the query endpoint). Available values:...
callback_urlCallback URL for task status changesOnce configured, the MiniMax server first sends a verification request containing a challenge field (you must return the challenge unchanged within 3 seconds to complete verification);...

Multimodal Content & Model Tokens (6)

Command / SyntaxWhat it doesNotes
"type": "text"Text prompt content item; every scenario must include oneInside the content array, with the prompt in the text field.
"type": "image_url"Image input content itemSupplies a reference or first-frame image to the generation.
"type": "video_url"Video input content itemSupplies a reference video to the generation.
"type": "audio_url"Audio input content itemSupplies reference audio to the generation.
rolePosition or purpose of a content itemConditionally required depending on the content type.
MiniMax-H3Current video generation model ID (Hailuo 03)Set as the model field value.

Chat API Parameters (12)

Command / SyntaxWhat it doesNotes
modelModel IDJSON body field of the OpenAI-compatible chat endpoint.
service_tierService tier for request admissionSupported values are standard and priority. If omitted, the request uses the standard tier. The priority price is 1.5 times the standard price and ensures priority admission so the...
messagesA list of messages containing the conversation historySupports text, image, video, and tool call content.
thinkingControls MiniMax-M3 thinkingWhen omitted, adaptive thinking is enabled by default and responses include thinking content. For M2.x models, thinking cannot be disabled.
reasoning_splitOutput-format switchWhen enabled, separates thinking content into the reasoning_content and reasoning_details fields. This does not enable or disable thinking.
streamWhether to use streaming output, defaults to falseWhen set to true, the response will be returned in chunks.
stream_optionsStreaming response optionsJSON body field of the OpenAI-compatible chat endpoint.
max_completion_tokensSpecifies the upper limit for generated content length, in tokensFor MiniMax-M3 the recommended value is 131072 (128K) and the maximum is 524288 (512K); for other models the recommended value is 65536 (64K) and the maximum is 204800 (200K). If...
temperatureTemperature coefficient, affects output randomnessRange [0, 2], default 1. Higher values produce more random output; lower values produce more deterministic output.
top_pNucleus sampling parameterRange [0, 1]. Default is 0.95 for MiniMax-M3 and 0.9 for M2.x models.
toolsTool definition listFunction tools are supported.
max_tokensLegacy generation length limit parameterDeprecated; use max_completion_tokens instead.

Frequently Asked Questions

How do I pass a prompt to MiniMax video generation?

As a content item with type text. The reference is explicit that every scenario must include one text item; image, video, and audio items are references added alongside it.

Which model IDs are current?

MiniMax-H3 is the listed video generation model (Hailuo 03). Chat model IDs are set through the model field on the OpenAI-compatible endpoint.

Is video generation synchronous?

No. The endpoint returns a task_id; poll the query task endpoint or configure callback_url for status notifications.

Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.

Related prompt references

Kling AI (24) · Vidu (24) · DeepSeek (22) · All AI prompt references