impulse

Auto Caption

Video
API id auto-caption
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 Auto Caption. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
auto-caption
-

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 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 fal's API.

Python
from litellm import completion

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

Quick answers

Which APIs offer Auto Caption?

Auto Caption runs on 1 API: fal.

Is Auto Caption being retired?

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

What is Auto Caption's API model id?

Use auto-caption with fal.

Sources

Raw catalog entry for auto-caption on fal
{
  "litellm_provider": "fal_ai",
  "mode": "video_generation",
  "output_cost_per_video": 0.1,
  "source": "https://fal.ai/models/fal-ai/auto-caption",
  "supported_endpoints": [
    "/v1/videos"
  ],
  "supported_modalities": [
    "text",
    "video"
  ],
  "supported_output_modalities": [
    "video"
  ]
}