Skip to main content
POST
/
list-models
curl -X POST https://api.magpipe.ai/functions/v1/list-models \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

{
  "models": [
    {
      "id": "gpt-4.1-nano",
      "name": "GPT-4.1 Nano",
      "provider": "openai",
      "description": "Fastest response time, optimized for voice",
      "latency": "lowest",
      "is_default": true
    },
    {
      "id": "gpt-4o-mini",
      "name": "GPT-4o Mini",
      "provider": "openai",
      "description": "Fast and cost-effective",
      "latency": "low",
      "is_default": false
    },
    {
      "id": "gpt-4o",
      "name": "GPT-4o",
      "provider": "openai",
      "description": "Most capable, higher latency",
      "latency": "medium",
      "is_default": false
    }
  ]
}
Retrieve all LLM models available for your AI agents to use during conversations.

​
Request Body

​
provider
string
Filter by provider: openai.

​
Response

​
models
array
Array of model objects.

​
Model Object

​
id
string
Model identifier to use in agent configuration.
​
name
string
Model display name.
​
provider
string
Model provider: openai.
​
description
string
Brief description of the model’s characteristics.
​
latency
string
Expected latency level: lowest, low, or medium.
​
is_default
boolean
Whether this is the default model for new agents.
curl -X POST https://api.magpipe.ai/functions/v1/list-models \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

{
  "models": [
    {
      "id": "gpt-4.1-nano",
      "name": "GPT-4.1 Nano",
      "provider": "openai",
      "description": "Fastest response time, optimized for voice",
      "latency": "lowest",
      "is_default": true
    },
    {
      "id": "gpt-4o-mini",
      "name": "GPT-4o Mini",
      "provider": "openai",
      "description": "Fast and cost-effective",
      "latency": "low",
      "is_default": false
    },
    {
      "id": "gpt-4o",
      "name": "GPT-4o",
      "provider": "openai",
      "description": "Most capable, higher latency",
      "latency": "medium",
      "is_default": false
    }
  ]
}