Skip to main content
The model/list API returns available models with their capabilities, reasoning effort options, and upgrade paths.

​
List Models

Fetch available models with optional pagination and filtering.

​
Method

model/list

​
Parameters

​
cursor
string
Opaque pagination cursor from previous response
​
limit
number
Page size (server defaults if unset)
​
includeHidden
boolean
default:false
When true, include models with hidden: true

​
Response

​
data
Model[]
Array of model objects
​
nextCursor
string | null
Cursor for next page (null if no more pages)

​
Model Object

​
id
string
Unique model identifier
​
model
string
Model name (e.g., gpt-5.1-codex)
​
displayName
string
Human-readable model name
​
description
string
Model description
​
hidden
boolean
Whether the model is hidden from default picker
​
isDefault
boolean
Whether this is the default model (only one model should be marked default)
​
supportsPersonality
boolean
Whether the model supports personality customization
​
inputModalities
InputModality[]
Supported input modalities (e.g., ["text", "image"])
​
supportedReasoningEfforts
ReasoningEffortOption[]
Available reasoning effort levels
​
defaultReasoningEffort
string
Default reasoning effort for this model (low, medium, high)
​
upgrade
string | null
Legacy upgrade model ID (deprecated)
​
upgradeInfo
ModelUpgradeInfo | null
Model upgrade information
​
availabilityNux
ModelAvailabilityNux | null
Model availability message

​
Example

{
  "method": "model/list",
  "id": 6,
  "params": {
    "cursor": null,
    "limit": 25,
    "includeHidden": false
  }
}

​
Reasoning Effort

Models support different reasoning effort levels that affect response quality and latency.

Low

Fast responses with minimal reasoningBest for: Quick edits, simple queries

Medium

Balanced performance and qualityBest for: General development tasks

High

Deep reasoning for complex problemsBest for: Architecture, debugging, optimization

​
Setting Reasoning Effort

You can set the reasoning effort at the thread or turn level: 
{
  "method": "thread/start",
  "id": 10,
  "params": {
    "model": "gpt-5.1-codex",
    "effort": "high"
  }
}

​
Input Modalities

Models may support different input modalities:
​
text
modality
Text input (all models)
​
image
modality
Image input (vision-capable models)
​
audio
modality
Audio input (audio-capable models)

​
Model Selection

When selecting a model, consider:
  1. Task complexity: Use higher reasoning effort for complex problems
  2. Input type: Ensure the model supports your input modality (text, images)
  3. Personality: Check supportsPersonality if you want to customize the agent’s tone
  4. Availability: Check availabilityNux for plan requirements
  5. Default: Start with isDefault: true model if unsure

​
Next Steps

Skills

List and manage skills

Apps

Discover and use apps