Skip to content
Last updated

🔨 In Development — This section is still being developed and may change.
**POST** `/v1/assistants` - Create a new AI assistant with custom configuration, tools, and behavior rules.
POSThttps://api.freddy.aitronos.com/v1/assistants

Request Body

name string required

The name of the assistant. Must be unique within the organization.

organization_id string required

The unique identifier of the organization to create the assistant in.

description string optional

A brief description of the assistant's purpose and capabilities.

model string optional · Defaults to gpt-4o

The AI model to use for this assistant. View available models →

allowed_model_providers array optional

Array of model provider identifiers that this assistant is allowed to use. When specified, the assistant will only be able to use models from these providers. Example: ["openai", "anthropic", "aitronos"].

instructions string optional

System instructions that define the assistant's behavior and personality.

tools array optional

Array of tools the assistant can use. Learn more about tools →

vector_store_ids array optional

Array of vector store IDs for file search capabilities.

access_mode string optional · Defaults to private

Access control for the assistant. One of public, private, organization.

temperature number optional · Defaults to 0.7

Controls randomness in responses (0.0 to 2.0).

max_output_synapses integer optional · Defaults to 4000

Maximum output length in synapses (neurons). Learn more


avatar_id string optional

Predefined avatar identifier from the Aitronos avatar library. View available avatars →

avatar string optional

Custom avatar URL. Used when you want to provide your own avatar image instead of using a predefined one.

tool_configurations object optional

Detailed configuration for built-in system tools. Use this for fine-grained control over tool behavior.

Show tool configurations

systemTools object

Built-in Aitronos tools configuration.

webSearch object · mode: on/off/auto, sources: boolean

codeInterpreter object · mode: on/off/auto, outputs: boolean

fileSearch object · mode: on/off/auto, results: boolean

computerUsePreview object · mode: on/off/auto, imageUrl: boolean

imageGeneration object · mode: on/off/auto, provider: openai/clipdrop

fileRetrieval object · mode: on/off/auto

mcpTools array

Enable the assistant to utilize external tools through Model Context Protocol (MCP) server integrations. Learn more about MCP

Show properties

serverLabel string required

Identifier label for the MCP server, used for recognition during tool invocations.

type string required

The type of the MCP tool. Always mcp.

allowedTools array or object optional

Specify permitted tools either as a string array or filter configuration object.

Show possible types

MCP allowed tools array

String array containing names of permitted tools.

MCP tool filter object

Filter configuration defining which tools are permitted.

Show properties

readOnly boolean optional

Determines if a tool performs data modifications or operates in read-only mode. Matches MCP servers annotated with readOnlyHint.

toolNames array optional

Array of permitted tool identifiers.

authorization string optional

OAuth bearer token for authenticating with remote MCP servers (custom URLs or service connectors). Your application manages the OAuth flow and supplies the token.

connectorId string optional

Service connector identifier for pre-integrated platforms. Either serverUrl or connectorId is required.

Examples: connector_googledrive, connector_gmail

View all supported connectors →

headers object optional

Custom HTTP headers transmitted to the MCP server for authentication or additional metadata.

requireApproval object or string optional · Defaults to always

Define approval requirements for MCP server tools.

Show possible types

MCP tool approval filter object

Configure tool-specific approval policies using always, never, or conditional filter rules.

Show properties

always object optional

Filter rules defining tools that always require approval.

Show properties

readOnly boolean optional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

toolNames array optional

List of allowed tool names.

never object optional

Filter rules defining tools that never require approval.

Show properties

readOnly boolean optional

Indicates whether or not a tool modifies data or is read-only. If an MCP server is annotated with readOnlyHint, it will match this filter.

toolNames array optional

List of allowed tool names.

MCP tool approval setting string

Universal approval policy for all tools. Set to always to mandate approval for every tool, or never to bypass all approval requirements.

serverDescription string optional

Descriptive text providing additional context about the MCP server's purpose.

serverUrl string optional

HTTP endpoint for the MCP server. Either serverUrl or connectorId is required.

streamlineTools array

Array of Streamline/Flow-Plate automation IDs.


system_message array optional

Pre-configured system messages or input examples. An array of input message objects with texts, images, or files.

context_strategy string optional · Defaults to auto

Sets the overall thread context management strategy. Values: full, off, auto, saver.

max_tool_calls integer optional · Defaults to 10

Maximum number of built-in tool calls allowed per response.

parallel_tool_calls boolean optional · Defaults to false

Whether the assistant can execute multiple tool calls simultaneously.

reasoning object optional

Configuration for reasoning models (o3-preview, o3-mini, gpt-5). Only applicable when using reasoning-capable models.

Show reasoning properties

effort string · Defaults to medium

Computational effort for reasoning. Values: minimal, low, medium, high.

summary string · Defaults to auto

Request reasoning summaries. Values: auto, concise, detailed.


service_tier string optional · Defaults to auto

Processing tier for requests. Values: auto, default, flex, priority.

store boolean optional · Defaults to false

Whether to store generated responses for later retrieval via API.

text_configuration object optional

Configuration for text response formatting and structured outputs. Learn more

top_logprobs integer optional

Number of alternative tokens to return at each position with log probabilities (0-20).

top_p number optional · Defaults to 1.0

Nucleus sampling probability mass (0.0-1.0). Alternative to temperature for controlling randomness.

truncation string optional · Defaults to auto

Strategy for handling inputs exceeding context window. Values: auto (truncate from beginning), disabled (fail with error).

metadata object optional

Custom key-value pairs for organizing and filtering assistants. Max 16 keys, each key ≤ 64 chars, each value ≤ 512 chars.

Bash
curl https://api.freddy.aitronos.com/v1/assistants \
  -H "Authorization: Bearer $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "My Assistant",
    "organization_id": "org_abc123"
  }'

Response

Returns

The created Assistant object with all configuration details.

{
  "id": "asst_abc123",
  "name": "Research Assistant",
  "description": "AI assistant for research and analysis",
  "model": "gpt-4o",
  "instructions": "You are a research assistant that helps find and analyze information.",
  "tools": [
    {
      "type": "web_search",
      "searchContextSize": "large"
    },
    {
      "type": "code_interpreter"
    }
  ],
  "access_mode": "private",
  "is_active": true,
  "temperature": 0.3,
  "max_output_synapses": 4000,
  "created_at": "2024-01-15T10:30:00Z",
  "updated_at": "2024-01-15T10:30:00Z",
  "organization_id": "org_abc123",
  "created_by": "user_abc123"
}