# MiniMax H3 Text-to-Video (Async)

> MiniMax H3 Text-to-Video (Async) is a paid API for AI agents from fal.ai (queue) at fal-queue.mpp.tempo.xyz, paid per call via MPP, $0.36/call, status unknown (last checked 2026-10-30).

Generates a video clip from a text prompt using MiniMax H3, submitted asynchronously and returning a request ID for polling

## Facts

- Endpoint: POST https://fal-queue.mpp.tempo.xyz/minimax/h3/text-to-video?utm_source=zero.xyz
- Price: $0.36/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Provider: fal.ai (queue)
- Docs: https://fal.ai
- Website: https://fal.ai
- Tags: ai, media
- Canonical page: https://www.zero.xyz/c/fal-ai-queue-minimax-h3-text-to-video-async-67fd5562
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GRJEHibQ-9zMT1FsMTAkc

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability fal-ai-queue-minimax-h3-text-to-video-async-67fd5562 -d '<json body>'
```

Example prompt: Generate a video of a golden retriever running through a field of sunflowers at sunset, with a cinematic wide-angle look — submit it through MiniMax H3 and give me the request ID so I can check when it's ready.

## When to prefer this

Choose this endpoint when you need AI-generated video from a text description and the generation time may exceed ~100 seconds (making synchronous endpoints time out). MiniMax H3 is well-suited for high-quality cinematic video generation. Prefer this async queue variant over sync alternatives when generating longer or more complex video clips where waiting for a result ID and polling is acceptable.

## Known failure modes

- Invalid or missing text prompt returns a 400 error
- Insufficient USDC balance causes payment failure before job submission
- Queue overload may result in extended wait times before video is available
- Very long or ambiguous prompts may degrade video quality or cause generation failure
- Polling for result before processing is complete returns a pending/in-progress status

## How this service works

MiniMax H3 - text-to-video (async, dynamic pricing)

## Output

Returns a request_id immediately upon submission. The agent can poll the fal.ai queue status endpoint using this ID to retrieve the final result, which includes a URL to the generated video clip once processing is complete.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/fal-ai-queue-minimax-h3-text-to-video-async-67fd5562/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from fal-queue.mpp.tempo.xyz](https://www.zero.xyz/host/fal-queue.mpp.tempo.xyz/llms.txt)
