POST
/
v1
/
agent
/
execute
curl --request POST \
  --url https://api.vlm.run/v1/agent/execute \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "metadata": {
    "environment": "dev",
    "session_id": "<string>",
    "allow_training": true
  },
  "config": {
    "prompt": "<string>",
    "detail": "auto",
    "response_model": "<any>",
    "json_schema": {},
    "gql_stmt": "<string>",
    "max_retries": 3,
    "max_tokens": 4096,
    "temperature": 0,
    "confidence": false,
    "grounding": false
  },
  "urls": [
    "<string>"
  ],
  "file_ids": [
    "<string>"
  ],
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "callback_url": "<string>",
  "name": "<string>",
  "version": "<string>",
  "batch": true
}'
{
  "usage": {
    "elements_processed": 123,
    "element_type": "image",
    "credits_used": 123,
    "steps": 123,
    "message": "<string>"
  },
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "response": "<any>",
  "status": "pending"
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request to execute an agent.

​
name
string
required

Name of the agent

​
metadata
object

Optional metadata to pass to the model.

​
config
object

The VLM generation config to be used for /<dtype>/generate.

​
urls
string[] | null

The URLs of the files.

​
file_ids
string[] | null

The IDs of the uploaded files.

​
id
string

Unique identifier of the request.

​
created_at
string

Date and time when the request was created (in UTC timezone)

​
callback_url
string | null

The URL to call when the request is completed.

Minimum length: 1
​
version
string | null
default:latest

Version of the agent, defaults to latest.

​
batch
boolean
default:true

Whether to process the document in batch mode (async).

Response

201
application/json
Successful Response

Base prediction response for all API responses.

​
usage
object

The usage metrics for the request.

​
id
string

Unique identifier of the response.

​
created_at
string

Date and time when the request was created (in UTC timezone)

​
completed_at
string | null

Date and time when the response was completed (in UTC timezone)

​
response
any | null

The response from the model.

​
status
enum<string>
default:pending

The status of the job.

Available options:
pending,
enqueued,
running,
completed,
failed,
paused