Verify agent connection
curl --request POST \
--url https://api.calibrate.artpark.ai/agents/{agent_uuid}/verify-connection \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"model": "openai/gpt-4.1",
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}
'import requests
url = "https://api.calibrate.artpark.ai/agents/{agent_uuid}/verify-connection"
payload = {
"model": "openai/gpt-4.1",
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"success": true,
"error": "<string>",
"sample_response": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Agents
Verify agent connection
Verify an agent’s connection and persist the result when successful
POST
/
agents
/
{agent_uuid}
/
verify-connection
Verify agent connection
curl --request POST \
--url https://api.calibrate.artpark.ai/agents/{agent_uuid}/verify-connection \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '
{
"model": "openai/gpt-4.1",
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}
'import requests
url = "https://api.calibrate.artpark.ai/agents/{agent_uuid}/verify-connection"
payload = {
"model": "openai/gpt-4.1",
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}
headers = {
"X-API-Key": "<api-key>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"success": true,
"error": "<string>",
"sample_response": {}
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>"
}
]
}Authorizations
API key for authentication
Path Parameters
The agent whose connection to verify
Example:
"f47ac10b-58cc-4372-a567-0e02b2c3d479"
Body
application/json
Body for verifying an existing agent by ID. The endpoint (agent_url,
agent_headers) comes from the agent's stored config, so only the probe
inputs are accepted here.
Model to verify. Omit for a basic connection check. Provide it for a model-specific check before benchmarking that model
Example:
"openai/gpt-4.1"
Sample chat messages to send during verification. Omit to use the default probe
Show child attributes
Show child attributes
Example:
[{ "content": "Hello", "role": "user" }]