impulse

H3 Max

Video
API id h3_max
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve H3 Max. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
h3_max
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
ImagesText
Produces
Video

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Independent models

No similar Independent model keeps its key capabilities.

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

No similar open-weight match.

Call it

Using RunwayML's API.

Python
from litellm import completion

response = completion(
    model="runwayml/h3_max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer H3 Max?

H3 Max runs on 1 API: RunwayML.

Is H3 Max being retired?

No retirement date is scheduled for it on any API we track.

What is H3 Max's API model id?

Use h3_max with RunwayML.

Sources

Raw catalog entry for h3_max on RunwayML
{
  "litellm_provider": "runwayml",
  "metadata": {
    "comment": "8 credits per second at 768p, 5 at 480p @ $0.01 per credit"
  },
  "mode": "video_generation",
  "output_cost_per_second": 0.08,
  "output_cost_per_second_480p": 0.05,
  "source": "https://docs.dev.runwayml.com/guides/pricing/",
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "video"
  ]
}