---
title: "List supported LLM models"
method: GET
path: "/v3/ai-agents/models"
tags: ["v3", "ai-agents"]
---

# List supported LLM models

`GET /v3/ai-agents/models`

## Request

- Base URL: `https://api.mentium.io` (the document declares no server; this is the origin it was published from)
- URL: `https://api.mentium.io/v3/ai-agents/models`
- Auth: HTTP bearer

Returns all LLM models that can be selected when creating or updating an AI agent.

## Query parameters

- `agent_type` string, nullable: Filter models by agent type (e.g. 'phone', 'text'). Currently all models are supported across all agent types; this parameter is reserved for future filtering.

## Response `200`

Successful Response

- AIAgentModelResponse[]
  - `identifier` string, required: Model string used in API calls (matches LLMModel enum value)
  - `label` string, required: Human-readable model name
  - `capabilities` string[]: Feature flags the model supports (e.g. 'reasoning_effort'). The frontend uses these to conditionally show/hide settings.
  - `available_reasoning_efforts` string[]: Allowed reasoning effort values for this model (e.g. ['low', 'medium', 'high']). Empty means the model does not support reasoning effort.
  - `max_tokens_limit` integer, nullable: Maximum output tokens the model supports. None means unknown/unlimited. The frontend uses this to cap the max_tokens input.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/mentium/apis/mentium-api.md) - [All operations](https://skmtc.dev/mentium/apis/mentium-api/llms.txt) - [OpenAPI document](https://skmtc.dev/mentium/apis/mentium-api/revisions/b4ed8e59432e?raw)