TinyMCE AI Models

The agent-1 model automatically selects the best AI model for your request based on speed, quality, and cost. It’s the recommended choice for most use cases as it optimizes performance and cost automatically.

Available Models

TinyMCE AI supports multiple AI models from different providers. Each model has unique capabilities, performance characteristics, and cost profiles.

Limitations

Model availability depends on your subscription tier and service compatibility version. Some models may have specific limitations or requirements.

How Model Selection Works

The agent model (agent-1) automatically selects the best underlying model based on:

  • Request complexity – Simple queries use faster, cost-effective models

  • Content size – Larger content uses models with better context windows

  • Required capabilities – Web search and reasoning require compatible models

  • Cost optimization – Balances quality with cost efficiency

You can also specify a model directly in your API requests for more control.

Model Compatibility Versions

Models are organized by compatibility versions to ensure API stability. When new models are introduced or existing models are updated, they may be added to a new compatibility version.

How It Works

Compatibility versions allow TinyMCE AI to introduce new models and capabilities without breaking existing integrations. Each version maintains a stable set of models and capabilities.

Checking Compatibility

Check the /v1/models endpoint to see available models for your compatibility version. The API response includes model capabilities, limits, and availability.

Model Capabilities

Different models support different capabilities. Check the model information endpoint to see which capabilities are available for each model.

Enable real-time web search to access current information during conversations. Not all models support web search. Check model capabilities to see which models support this feature.

Reasoning

Enable step-by-step reasoning to see the AI’s problem-solving process. Some models have reasoning always enabled and cannot be turned off.

Always-on reasoning models:

  • Reasoning is always active during inference.

  • You cannot turn reasoning off via the API.

To determine if a model has always-on reasoning, check the API response when listing models. Models with mandatory reasoning will indicate this in their capability structure.

Please observe, that model names such as gpt-5, claude-4-sonnet, etc. are examples. Actual available models depend on your service’s compatibility version. Use the /v1/models endpoint to see current available models for your environment.

Web Scraping

Extract and process content from web pages for analysis and summarization.

Model Limitations

File Processing Limits

Files are limited to 7MB each (PDF, DOCX, PNG, JPEG, Markdown, HTML, Plain text). You can upload up to 100 files per conversation with a total size limit of 30MB. PDF files are limited to 100 pages total across all PDFs in a conversation.

Model-specific file limits

Anthropic and agent models may use files up to 5MB each.

Content Moderation

All models include moderation for inappropriate content, harmful instructions, personal information, copyrighted material, misinformation, sensitive topics, and security threats.

Model Descriptions

Model descriptions returned by the API are provided in English and may be updated over time to reflect model improvements or capability changes.

Translation and Localization

Backend translation handling for model descriptions is planned in a future release. Until then, use the approach described below.

If your application requires translated model descriptions, maintain a translation map in your code keyed by model.id, with fallback to the English description from the API for unknown models. This allows new models to work immediately while you add translations at your own pace.

Model Deprecation

Models scheduled for removal will include a removal field with an ISO 8601 date (e.g., "removal": "2025-11-17T00:00:00.000Z"). When a model is removed, API requests will fail with error code MODEL_NOT_FOUND and the models endpoint will stop returning that particular model.

API Examples

Model Selection

POST /v1/conversations/my-conversation-123/messages
Content-Type: application/json
Authorization: Bearer <your-token>

{
  "prompt": "Analyze this document and provide insights",
  "model": "agent-1",
  "content": [
    {
      "type": "document",
      "id": "doc-1234567890123"
    }
  ]
}

Capability Configuration

POST /v1/conversations/my-conversation-123/messages
Content-Type: application/json
Authorization: Bearer <your-token>

{
  "prompt": "Research the latest developments in AI",
  "model": "gpt-4o",
  "capabilities": {
    "webSearch": {},
    "reasoning": {}
  }
}

Model Information

Get all available models for compatibility version 1:

GET /v1/models/1
Authorization: Bearer <your-token>

Response:

{
  "items": [
    {
      "id": "agent-1",
      "name": "Agent",
      "provider": "Agent",
      "description": "Automatically selects the best model for speed, quality, and cost",
      "allowed": true,
      "capabilities": {
        "webSearch": {
          "enabled": true,
          "allowed": true
        },
        "reasoning": {
          "enabled": true,
          "allowed": true
        }
      },
      "limits": {
        "maxPromptLength": 30000,
        "maxConversationLength": 256000,
        "maxFiles": 100,
        "maxFileSize": 7000000,
        "maxTotalFileSize": 30000000,
        "maxTotalPdfFilePages": 100
      }
    }
  ]
}

API Reference

For complete documentation on model endpoints, compatibility versions, and capability schemas, see:

  • Conversations – Use models in interactive AI discussions.

  • Reviews – Apply models to content analysis and improvement.

  • Actions – Use models for content transformation tasks.