curl --request GET \
--url https://api.lunary.ai/v1/runs{
"total": 200,
"page": 1,
"limit": 10,
"data": [
{
"type": "llm",
"name": "gpt-5",
"createdAt": "2025-10-01T12:00:00Z",
"endedAt": "2025-10-01T12:00:03Z",
"duration": 3,
"tokens": {
"completion": 100,
"prompt": 50,
"total": 150
},
"feedback": null,
"status": "success",
"tags": [
"example"
],
"templateSlug": "example-template",
"templateVersionId": 1234,
"input": [
{
"role": "user",
"content": "Hello world!"
}
],
"output": [
{
"role": "assistant",
"content": "Hello. How are you?"
}
],
"error": null,
"user": {
"id": "11111111",
"externalId": "user123",
"createdAt": "2021-12-01T12:00:00Z",
"lastSeen": "2022-01-01T12:00:00Z",
"props": {
"name": "Jane Doe",
"email": "[email protected]"
}
},
"cost": 0.05,
"params": {
"temperature": 0.5,
"maxTokens": 100,
"tools": []
},
"metadata": null
}
]
}The Runs API endpoint allows you to retrieve data about specific runs from your Lunary application.
The most common run types are ‘llm’, ‘agent’, ‘chain’, ‘tool’, ‘thread’ and ‘chat’.
It supports various filters to narrow down the results according to your needs.
This endpoint supports GET requests and expects query parameters for filtering the results.
curl --request GET \
--url https://api.lunary.ai/v1/runs{
"total": 200,
"page": 1,
"limit": 10,
"data": [
{
"type": "llm",
"name": "gpt-5",
"createdAt": "2025-10-01T12:00:00Z",
"endedAt": "2025-10-01T12:00:03Z",
"duration": 3,
"tokens": {
"completion": 100,
"prompt": 50,
"total": 150
},
"feedback": null,
"status": "success",
"tags": [
"example"
],
"templateSlug": "example-template",
"templateVersionId": 1234,
"input": [
{
"role": "user",
"content": "Hello world!"
}
],
"output": [
{
"role": "assistant",
"content": "Hello. How are you?"
}
],
"error": null,
"user": {
"id": "11111111",
"externalId": "user123",
"createdAt": "2021-12-01T12:00:00Z",
"lastSeen": "2022-01-01T12:00:00Z",
"props": {
"name": "Jane Doe",
"email": "[email protected]"
}
},
"cost": 0.05,
"params": {
"temperature": 0.5,
"maxTokens": 100,
"tools": []
},
"metadata": null
}
]
}llm, trace, thread csv, jsonl asc, desc Successful response
Show child attributes
First message captured in the conversation thread, when available.
Total number of messages within the conversation thread.