# H3 API Pricing

As of October 10, 2026, H3 costs $0.13 per second of video on fal.

- Page: https://models.litellm.ai/models/h3
- LiteLLM model name: `fal_ai/minimax/h3/text-to-video`
- Added to LiteLLM: September 21, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| fal | `fal_ai/minimax/h3/text-to-video` | – | – | – | – | $0.13 | – |
| fal | `fal_ai/minimax/h3/reference-to-video` | – | – | – | – | $0.13 | – |

## Cost examples

100 clips of 8 seconds each:

- fal: $104.00

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="fal_ai/minimax/h3/text-to-video",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does H3 cost?

H3 costs $0.13 per second of video on fal.

### Which providers offer H3?

H3 is available from fal through LiteLLM, using the model name fal_ai/minimax/h3/text-to-video.

### How do I call H3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="fal_ai/minimax/h3/text-to-video", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/videos from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add H3?

H3 was added to LiteLLM's model price file on September 21, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json