impulse

Veo3.1 Fast Extend Video

Frontier labVideo
API id extend-video
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 Veo3.1 Fast Extend Video. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
extend-video
-

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
TextVideo
Produces
Video

Similar models

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

Smaller Google models

No similar Google 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 fal's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Veo3.1 Fast Extend Video?

Veo3.1 Fast Extend Video runs on 1 API: fal.

Is Veo3.1 Fast Extend Video being retired?

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

What is Veo3.1 Fast Extend Video's API model id?

Use extend-video with fal.

Sources

Raw catalog entry for extend-video on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "comment": "per second of generated video with the default generate_audio=true ($0.15); videos without audio are $0.10 per second, which has no catalog field"
  },
  "mode": "video_generation",
  "output_cost_per_second": 0.15,
  "source": "https://fal.ai/models/fal-ai/veo3.1/fast/extend-video",
  "supported_endpoints": [
    "/v1/videos"
  ],
  "supported_modalities": [
    "text",
    "video"
  ],
  "supported_output_modalities": [
    "video"
  ]
}