MiniMax H3 API Pricing
minimax/MiniMax-H3- Price
- $0.08 per second of video
As of October 21, 2026, MiniMax H3 costs $0.08 per second of video on MiniMax.
MiniMax H3 pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Per second | Context |
|---|---|---|---|
| MiniMax | minimax/MiniMax-H3 | $0.08 | – |
Other MiniMax H3 prices on MiniMax
| Input image | $0.04 per image |
What MiniMax H3 costs in practice
100 clips of 8 seconds each
| MiniMax | $64.00 |
MiniMax H3 features
Input: text, image, audio. Output: video.
Use MiniMax H3 with LiteLLM
Call MiniMax H3 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/videos. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="minimax/MiniMax-H3",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: minimax-h3
litellm_params:
model: minimax/MiniMax-H3
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "minimax-h3",
"messages": [{"role": "user", "content": "Hello!"}]
}'MiniMax H3 FAQ
How much does MiniMax H3 cost?
MiniMax H3 costs $0.08 per second of video on MiniMax.
Which providers offer MiniMax H3?
MiniMax H3 is available from MiniMax through LiteLLM, using the model name minimax/MiniMax-H3.
How do I call MiniMax H3 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="minimax/MiniMax-H3", 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 MiniMax H3?
MiniMax H3 was added to LiteLLM's model price file on October 15, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: MiniMax.
Provider pages: MiniMax.
