Sign in
v1 inference (deprecated)

[Deprecated] Generate completion with memory context

⚠️ DEPRECATED — Use POST /v1/chat/completions or POST /v1/text/generations instead.

This endpoint is kept for backward compatibility and internally delegates to
the new text generation handler.
post/v1/inference/completion

Request body

user_idstring required

User ID (always required)

persona_idstring nullable

Optional persona ID. If provided, inference uses this persona's context instead of the user

project_idstring nullable

Optional project ID. If provided, inference uses project context (inherits from user)

session_idstring nullable

Session ID

modelstring

LLM model to use for generation

disabled_learningboolean

Whether to disable learning

Example request

{
  "content": [
    {
      "content": "You are a helpful AI assistant.",
      "role": "system"
    },
    {
      "content": "Hello, how are you?",
      "role": "user"
    }
  ],
  "disabled_learning": false,
  "model": "gpt-4.1-mini",
  "session_id": "session-abc",
  "user_id": "user-123"
}

Response

Successful Response

messagesobject[] nullable

Formatted messages with memory context

responsestring nullable

Generated response content

Example response

{
  "messages": [
    {
      "content": "You are a helpful AI assistant...",
      "role": "system"
    },
    {
      "content": "Hello, how are you?",
      "role": "user"
    },
    {
      "content": "I'm doing well, thank you for asking. How can I help you today?",
      "role": "assistant"
    }
  ],
  "response": "I'm doing well, thank you for asking. How can I help you today?"
}

Changes