Invoke an agent

Execute a one-shot task with an agent. This endpoint is designed for task-oriented operations

where you provide input and receive a complete output.

Use cases:

  • Data analysis and processing
  • Content generation (with streaming for long outputs)
  • One-time operations that don't require conversation history
  • API-like operations

Streaming: Set stream: true in the request body to receive Server-Sent Events (SSE) stream with incremental chunks. Useful for long-running tasks or real-time progress updates.

POST
/agents/{name}/invoke
AuthorizationBearer <token>

Project API key

In: header

Path Parameters

name*string

Unique, URL-safe agent name within the project

Request Body

application/json

input*

Input data for the agent. Structure depends on agent implementation.

stream?boolean

Whether to stream the response as SSE.

Defaultfalse
context?

Optional request context passed to the agent handler.

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

curl -X POST "https://api.reminix.ai/v1/agents/string/invoke" \  -H "Content-Type: application/json" \  -d '{    "input": {      "task": "analyze this data",      "data": {        "value": 123,        "items": [          "a",          "b",          "c"        ]      }    },    "stream": false  }'
{
  "output": "Analysis complete. Found 3 trends in the data."
}
{
  "error": "Invalid request"
}
{
  "error": "Invalid or missing API key"
}
{
  "error": "Resource not found"
}
{
  "error": "Internal server error"
}
{
  "error": "Unable to reach agent machine. The deployment may be down."
}
{
  "error": "Request timeout - agent took too long to respond"
}