impulse

Veo3

Frontier labVideo
API id veo3
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. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
veo3
-

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 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.

Model line

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

  1. UndatedVeo3.1LatestNot listed
  2. UndatedVeo3This pageNot listed

Call it

Using fal's API.

Python
from litellm import completion

response = completion(
    model="fal_ai/veo3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Veo3?

Veo3 runs on 1 API: fal.

Is Veo3 being retired?

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

Is there a newer version of Veo3?

Yes. Veo3.1 is the newest model in this line.

What is Veo3's API model id?

Use veo3 with fal.

Sources

Raw catalog entry for veo3 on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "comment": "per second of generated video with the default generate_audio=true ($0.40); videos without audio are $0.20 per second, which has no catalog field"
  },
  "mode": "video_generation",
  "output_cost_per_second": 0.4,
  "source": "https://fal.ai/models/fal-ai/veo3",
  "supported_endpoints": [
    "/v1/videos"
  ],
  "supported_modalities": [
    "text"
  ],
  "supported_output_modalities": [
    "video"
  ]
}