H3 Max

Facts

Model name
h3-max
Maker
MiniMax
Context window
32K tokens
Price
$0.050 to $0.080 per second
Providers
1 independent provider
Regions
us

Providers

Request

curl https://router.inference.ai.exchange/v1/videos \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "h3-max",
    "prompt": "a red paper boat on a stream"
  }'

Questions

What is H3 Max?
H3 Max is a model from MiniMax.
How much does H3 Max cost?
Offers now ask $0.050 to $0.080 second.
What is the context length of H3 Max?
The largest offer takes 32,000 input tokens. One job can generate up to 1 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can H3 Max do?
Its providers list Vision, Text.
What inputs and outputs does H3 Max support?
Text · Images → Text · Video.
Which providers serve H3 Max?
1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call H3 Max?
Send "h3-max" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was H3 Max listed?
The exchange first listed it on 11/7/2026. This is not its release date.

Related pages