Skip to main content
POST
/
api
/
content
/
analyze
cURL
curl --request POST \
  --url https://recoup-api.vercel.app/api/content/analyze \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "video_url": "<string>",
  "prompt": "<string>",
  "temperature": 0.2,
  "max_tokens": 2048
}
'
{
  "text": "<string>",
  "finish_reason": "stop",
  "usage": {
    "output_tokens": 123
  }
}

Authorizations

​
x-api-key
string
header
required

Your Recoup API key. Learn more.

Body

application/json

Video analysis parameters

​
video_url
string<uri>
required

Publicly accessible URL of the video to analyze. Supported formats: MP4, MOV, AVI, and other FFmpeg-compatible formats. Maximum duration: 1 hour.

​
prompt
string
required

A text prompt that guides the analysis. Can be instructive, descriptive, or phrased as a question. Examples: "Describe the key moments in this video", "Generate 5 SEO keywords for this video".

Maximum string length: 2000
​
temperature
number
default:0.2

Controls the randomness of the text output. Lower values produce more focused results. Defaults to 0.2.

Required range: 0 <= x <= 1
​
max_tokens
integer

Maximum number of tokens to generate. If omitted, uses the model default.

Required range: 1 <= x <= 4096

Response

Video analyzed successfully

​
text
string
required

The generated analysis text based on the video and prompt.

​
finish_reason
enum<string> | null

stop if the generation completed normally. length if truncated at the token limit.

Available options:
stop,
length
​
usage
object