impulse

Heygen V2 Video Agent

Video
API id video-agent
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 Heygen V2 Video Agent. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
video-agent
-

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
Text
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.

Model line

Newer and older versions, at each lab's own price.

  1. UndatedHeygen V3 Video AgentLatestNot listed
  2. UndatedHeygen V2 Video AgentThis pageNot listed

Call it

Using fal's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Heygen V2 Video Agent?

Heygen V2 Video Agent runs on 1 API: fal.

Is Heygen V2 Video Agent being retired?

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

Is there a newer version of Heygen V2 Video Agent?

Yes. Heygen V3 Video Agent is the newest model in this line.

What is Heygen V2 Video Agent's API model id?

Use video-agent with fal.

Sources

Raw catalog entry for video-agent on fal
{
  "litellm_provider": "fal_ai",
  "mode": "video_generation",
  "output_cost_per_second": 0.034,
  "source": "https://fal.ai/models/fal-ai/heygen/v2/video-agent",
  "supported_endpoints": [
    "/v1/videos"
  ],
  "supported_modalities": [
    "text"
  ],
  "supported_output_modalities": [
    "video"
  ]
}