Models

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

string

Opaque pagination cursor from previous response

number

Page size (server defaults if unset)

boolean

default:false

When true, include models with hidden: true

Response

Model[]

Array of model objects

string | null

Cursor for next page (null if no more pages)

Model Object

string

Unique model identifier

string

Model name (e.g., gpt-5.1-codex)

string

Human-readable model name

string

Model description

boolean

Whether the model is hidden from default picker

boolean

Whether this is the default model (only one model should be marked default)

boolean

Whether the model supports personality customization

InputModality[]

Supported input modalities (e.g., ["text", "image"])

ReasoningEffortOption[]

Available reasoning effort levels

Show ReasoningEffortOption

string

Effort level: low, medium, or high

string

Human-readable effort name

string

Effort description

string

Default reasoning effort for this model (low, medium, high)

string | null

Legacy upgrade model ID (deprecated)

ModelUpgradeInfo | null

Model upgrade information

Show ModelUpgradeInfo

string

Recommended upgrade model

string

Upgrade message text

string

URL to model information

string

Markdown migration guide

ModelAvailabilityNux | null

Model availability message

Show ModelAvailabilityNux

string

Availability message (e.g., “Upgrade to Pro for access”)

Example

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

{
  "id": 6,
  "result": {
    "data": [
      {
        "id": "gpt-5.1-codex",
        "model": "gpt-5.1-codex",
        "displayName": "GPT-5.1 Codex",
        "description": "Latest Codex model with advanced reasoning",
        "hidden": false,
        "isDefault": true,
        "supportsPersonality": true,
        "inputModalities": ["text", "image"],
        "supportedReasoningEfforts": [
          {
            "effort": "low",
            "displayName": "Low",
            "description": "Fast responses"
          },
          {
            "effort": "medium",
            "displayName": "Medium",
            "description": "Balanced performance"
          },
          {
            "effort": "high",
            "displayName": "High",
            "description": "Deep reasoning"
          }
        ],
        "defaultReasoningEffort": "medium",
        "upgrade": null,
        "upgradeInfo": null,
        "availabilityNux": null
      },
      {
        "id": "gpt-5-codex",
        "model": "gpt-5-codex",
        "displayName": "GPT-5 Codex",
        "description": "Previous generation Codex model",
        "hidden": false,
        "isDefault": false,
        "supportsPersonality": true,
        "inputModalities": ["text"],
        "supportedReasoningEfforts": [
          {
            "effort": "medium",
            "displayName": "Medium",
            "description": "Standard reasoning"
          }
        ],
        "defaultReasoningEffort": "medium",
        "upgrade": "gpt-5.1-codex",
        "upgradeInfo": {
          "model": "gpt-5.1-codex",
          "upgradeCopy": "Upgrade to GPT-5.1 Codex for improved performance",
          "modelLink": "https://openai.com/models/gpt-5-1-codex",
          "migrationMarkdown": "## Migration Guide\n\nGPT-5.1 offers..."
        },
        "availabilityNux": null
      }
    ],
    "nextCursor": null
  }
}

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"
  }
}

{
  "method": "turn/start",
  "id": 30,
  "params": {
    "threadId": "thr_123",
    "input": [{"type": "text", "text": "Optimize this algorithm"}],
    "effort": "high"
  }
}

Input Modalities

Models may support different input modalities:

modality

Text input (all models)

modality

Image input (vision-capable models)

modality

Audio input (audio-capable models)

Model Selection

When selecting a model, consider:

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

App Server API

TypeScript SDK

List Models

Method

Parameters

Response

Model Object

Example

Reasoning Effort

Low

Medium

High

Setting Reasoning Effort

Input Modalities

Model Selection

Next Steps

Skills

Apps

​List Models

​Method

​Parameters

​Response

​Model Object

​Example

​Reasoning Effort

Low

Medium

High

​Setting Reasoning Effort

​Input Modalities

​Model Selection

​Next Steps

Skills

Apps

List Models

Method

Parameters

Response

Model Object

Example

Reasoning Effort

Setting Reasoning Effort

Input Modalities

Model Selection

Next Steps