Hailuo AI / MiniMax · Rate Limits

Hailuo Ai Rate Limits

MiniMax does not publish a single fixed numeric rate-limit table for its developer APIs. Video generation is asynchronous and effectively governed by concurrent-task limits and your account's video-point balance rather than a per-minute request cap: you create a task, then poll GET /query/video_generation (MiniMax recommends about a 10-second polling interval to avoid unnecessary load). Text/chat and text-to-speech APIs are governed by per-account requests-per-minute and tokens/characters-per-minute quotas that vary by model and account tier. Concrete numeric limits should be confirmed in the console.

Hailuo Ai Rate Limits is the machine-readable rate-limit profile for Hailuo AI / MiniMax on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 5 rate-limit definitions, measuring tasks, requests, and seconds.

The profile also includes 3 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include Video Generation, AI Video, Generative AI, Rate Limiting, and Quotas.

5 Limits Throttle: 429
Video GenerationAI VideoGenerative AIRate LimitingQuotas

Limits

Video Generation Concurrent Tasks account
tasks
not published (tier-dependent)
Async video tasks are bounded by concurrent-task limits and video-point balance rather than a request-rate cap.
Video Task Polling account
requests
recommended ~1 request / 10 seconds per task
MiniMax recommends a ~10-second polling interval on GET /query/video_generation.
Chat / LLM Requests account
requests
per-model RPM (not published)
Requests-per-minute and tokens-per-minute quotas vary by model and account tier.
Text-to-Speech Requests account
requests
per-model RPM (not published)
T2A HTTP and WebSocket are bounded by per-account concurrency and character throughput.
Download URL Validity file
seconds
32400
Retrieved video download URLs expire after about 9 hours; persist assets promptly.

Policies

Asynchronous Backpressure
Video generation is queued (Queueing/Preparing/Processing); throughput is managed by the task queue rather than by rejecting requests outright.
Backoff Strategy
Clients should poll on the recommended interval and implement exponential backoff with jitter, honoring Retry-After on 429 responses.
No Charge on Failure
Failed generations and clips blocked by security review do not consume video points.

Sources