Predefined and Custom Models

Configure LLM models for your agents - use default models or bring your own API keys

Odin AI not only brings you the latest and most popular models available, we enable you to connect to your own custom model with our “Bring Your Own Keys” (BYOK) feature. This gives you the ability to create custom Agents and test how they respond or complete the tasks you give them so that you can use the LLM that produces the best results for your use case. In this article you’ll learn about the different LLMs that are available and how to connect your own custom LLM to your Agents.

Your agents can use two types of models:

• Predefined Models - Pre-configured models available to all users
• Custom Models - Models you configure with your own API keys (BYOK)

Predefined Models

Predefined models are available by default and don’t require API key configuration. These models are managed by Odin and are ready to use.

Odin provides access to a wide range of models from leading AI providers, including OpenAI, Anthropic, Google AI, and more. The full list of available models is displayed in the model selector when configuring your agent.

Frontier Models

Frontier models represent the latest and most advanced AI capabilities available. These cutting-edge models offer superior performance for complex tasks:

OpenAI Frontier Models

• GPT-4o - Latest GPT-4 model with improved performance, faster responses, and enhanced capabilities
• O1 Mini - Advanced reasoning model optimized for complex problem-solving and step-by-step thinking
• GPT-4 Turbo - High-performance model with extended context window

Anthropic Frontier Models

• Claude 3.5 Sonnet - Latest Claude model with advanced reasoning, long context (200K tokens), and superior performance
• Claude 3 Opus - Most capable Claude model for complex, nuanced tasks requiring deep understanding

Google AI Frontier Models

• Gemini Pro - Google’s latest advanced language model with multimodal capabilities and extended context

Other Available Models

In addition to frontier models, Odin provides access to a comprehensive selection of models including:

• GPT-3.5 Turbo - Fast and cost-effective option for general tasks
• Claude 3 Haiku - Fast and efficient Claude model
• Llama 3 - Open-source models (8B and 70B variants)
• Mixtral - High-performance open-source model
• DeepSeek - Advanced reasoning model
• And many more…

All available models are visible in the model selector dropdown when configuring your agent. Models are organized by provider and show their cost, capabilities, and availability status.

Model Selection

1. Navigate to Agents in the sidebar
2. Select or create an agent
3. Click Edit to open the agent builder
4. Go to the General tab
5. Find the Model section
6. Select a predefined model from the dropdown

Model Information

Each predefined model shows:

• Model Name - Display name (e.g., “GPT-4o”)
• Provider - API provider (OpenAI, Anthropic, Google AI)
• Cost - Credits per use
• Status - Available or requires upgrade

Custom Models (BYOK)

Bring Your Own Key (BYOK) allows you to configure custom models using your own API keys. This gives you:

• Cost Control - Use your own API keys and billing
• Model Flexibility - Access models not available in predefined list
• Custom Endpoints - Connect to private or custom model endpoints
• Provider Choice - Use any compatible API provider

Supported Providers

OpenAI

• Standard OpenAI API models
• Azure OpenAI endpoints
• Custom OpenAI-compatible endpoints

Configuration:

• API Key: Your OpenAI API key
• API URL: https://api.openai.com/v1 (default)
• Model Name: e.g., gpt-4, gpt-3.5-turbo

Anthropic

• Claude models via Anthropic API
• Custom Anthropic-compatible endpoints

Configuration:

• API Key: Your Anthropic API key
• API URL: https://api.anthropic.com (default)
• Model Name: e.g., claude-3-5-sonnet-20241022

Google AI

• Gemini models via Google AI API
• Custom Google AI endpoints

Configuration:

• API Key: Your Google AI API key
• API URL: https://generativelanguage.googleapis.com/ (default)
• Model Name: e.g., gemini-pro

OpenRouter

• Access to multiple model providers through OpenRouter
• Unified API for various models

Configuration:

• API Key: Your OpenRouter API key
• API URL: OpenRouter endpoint
• Model Name: Any model available on OpenRouter

AWS Bedrock

• Amazon Bedrock models
• Access to various foundation models

Configuration:

• AWS credentials configured separately
• API URL: Bedrock endpoint
• Model Name: Bedrock model identifier

Custom Endpoints

• Any OpenAI-compatible API endpoint
• Private model deployments
• Self-hosted models

Configuration:

• API Key: Your custom API key (if required)
• API URL: Your custom endpoint URL
• Model Name: Your model identifier

Adding Custom Models

Step 1: Access Model Configuration

1. Navigate to Agents in the sidebar
2. Select or create an agent
3. Click Edit to open the agent builder
4. Go to the General tab
5. Scroll to the AI Models section
6. Click the Custom tab

Step 2: Add New Model

1. Click Add Custom Model button
2. The model configuration modal will open

Step 3: Configure Model Settings

Basic Information

Model Name

• Enter a descriptive name for your model
• Example: “My GPT-4”, “Company Claude”, “Custom Model”

Model Version/ID

• Enter the model identifier
• Example: gpt-4, claude-3-5-sonnet-20241022, gemini-pro
• This is the actual model name used in API calls

API Configuration

API Provider

• Select your API provider from the dropdown:
  • OpenAI
  • Anthropic
  • Google AI
  • OpenRouter
  • AWS Bedrock
  • Custom

API Key

• Enter your API key for the selected provider
• Keys are stored securely and encrypted
• Required for most providers

API URL

• Enter the API endpoint URL
• Default URLs are pre-filled based on provider
• For custom endpoints, enter your full URL

API Version (Optional)

• For Azure OpenAI, specify API version
• Example: 2024-12-01-preview

Model Limits

Max Input Tokens

• Maximum tokens the model can accept as input
• Example: 60000, 100000, 200000
• Default: 3000

Max Response Tokens

• Maximum tokens the model can generate
• Example: 4096, 8000, 16000
• Default: 1000

Advanced Settings

Custom Headers (Optional)

• Add custom HTTP headers if required
• Example: X-Custom-Header: value
• Useful for custom authentication or metadata

Model Extra Parameters (Optional)

• Additional parameters for model configuration
• JSON format
• Provider-specific settings

Step 4: Save Model

1. Review all configuration settings
2. Click Save or Add Model
3. The model is now available in your Custom models list

Using Custom Models

Selecting a Custom Model

1. In the General tab, find the Model section
2. The dropdown shows both predefined and custom models
3. Custom models are marked or shown in a separate section
4. Select your custom model

Model Availability

• Custom models are project-specific
• Models are available to all agents in the project
• Each project can have its own set of custom models

Managing Custom Models

Viewing Custom Models

1. Go to Agents → Edit Agent → General tab
2. Click the Custom tab in the AI Models section
3. See all your custom models listed

Editing Custom Models

1. Find the model in the Custom models list
2. Click the Edit icon (three dots menu)
3. Modify configuration settings
4. Click Save to update

Editing the API key will replace the existing key. Make sure you have the correct key before saving.

Deleting Custom Models

1. Find the model in the Custom models list
2. Click the Delete icon (three dots menu)
3. Confirm deletion
4. The model is removed from your project

Deleting a custom model will affect all agents using that model. Make sure to update those agents first.

Model Configuration Examples

Example 1: OpenAI Custom Model

{
  "model_name": "My GPT-4",
  "version": "gpt-4",
  "api_provider": "openai",
  "api_type": "openai",
  "api_key": "sk-...",
  "api_url": "https://api.openai.com/v1",
  "max_input_tokens": 60000,
  "max_response_tokens": 4096
}

Example 2: Azure OpenAI

{
  "model_name": "Azure GPT-4",
  "version": "gpt-4",
  "api_provider": "openai",
  "api_type": "azure",
  "api_key": "your-azure-key",
  "api_url": "https://your-resource.openai.azure.com",
  "api_version": "2024-12-01-preview",
  "max_input_tokens": 60000,
  "max_response_tokens": 4096
}

Example 3: Anthropic Claude

{
  "model_name": "Company Claude",
  "version": "claude-3-5-sonnet-20241022",
  "api_provider": "anthropic",
  "api_type": "anthropic",
  "api_key": "sk-ant-...",
  "api_url": "https://api.anthropic.com",
  "max_input_tokens": 60000,
  "max_response_tokens": 4000
}

Example 4: Custom Endpoint

{
  "model_name": "Private Model",
  "version": "custom-model-v1",
  "api_provider": "custom",
  "api_type": "custom",
  "api_key": "your-custom-key",
  "api_url": "https://your-custom-endpoint.com/v1",
  "max_input_tokens": 100000,
  "max_response_tokens": 8000,
  "auth_header_template": "{\"Authorization\": \"Bearer <API_KEY>\"}"
}

Best Practices

API Key Security

• Never Share Keys - Keep API keys confidential
• Use Environment Variables - For development, use secure storage
• Rotate Keys Regularly - Update keys periodically
• Monitor Usage - Track API usage to detect issues

Model Selection

• Match Use Case - Choose models appropriate for your task
• Consider Cost - Balance performance and cost
• Test Performance - Evaluate model quality for your needs
• Monitor Limits - Watch token limits and quotas

Configuration

• Accurate Model Names - Use exact model identifiers
• Correct URLs - Verify API endpoint URLs
• Appropriate Limits - Set realistic token limits
• Test Connections - Verify model connectivity

Cost Management

• Track Usage - Monitor API usage and costs
• Set Budgets - Configure spending limits if available
• Optimize Tokens - Use appropriate token limits
• Review Regularly - Audit model usage periodically

Troubleshooting

Model Not Available

Problem: Custom model doesn’t appear in dropdown

Possible Causes:

• Model not saved correctly
• API key invalid
• Model configuration error

Solutions:

• Verify model was saved successfully
• Check API key is correct
• Review model configuration
• Refresh the page

API Key Errors

Problem: “Invalid API key” or authentication errors

Possible Causes:

• Incorrect API key
• Expired API key
• Wrong API provider selected
• Key doesn’t have required permissions

Solutions:

• Verify API key is correct
• Check key hasn’t expired
• Confirm correct provider selected
• Ensure key has necessary permissions

Connection Failures

Problem: Cannot connect to model endpoint

Possible Causes:

• Incorrect API URL
• Network connectivity issues
• Endpoint not accessible
• Firewall blocking connection

Solutions:

• Verify API URL is correct
• Check network connectivity
• Ensure endpoint is accessible
• Review firewall rules

Token Limit Errors

Problem: “Token limit exceeded” errors

Possible Causes:

• Input too long
• Response limit too high
• Model limits exceeded

Solutions:

• Reduce input length
• Lower max response tokens
• Check model’s actual limits
• Split large inputs

Model Compatibility

Knowledge Base v2

When using Knowledge Base v2, only certain models are supported:

• OpenAI models (openai, azure)
• Anthropic models

Other providers are not compatible with Knowledge Base v2.

Feature Support

Different models support different features:

• Streaming - Most models support streaming responses
• Function Calling - OpenAI and Anthropic models
• Vision - GPT-4 Vision, Claude 3, Gemini Pro Vision
• Long Context - Claude 3.5 Sonnet, GPT-4 Turbo

API Key Management

Getting API Keys

OpenAI

1. Go to OpenAI Platform
2. Navigate to API Keys
3. Create a new secret key
4. Copy the key (starts with sk-)

Anthropic

1. Go to Anthropic Console
2. Navigate to API Keys
3. Create a new key
4. Copy the key (starts with sk-ant-)

Google AI

1. Go to Google AI Studio
2. Create a new API key
3. Copy the key

OpenRouter

1. Go to OpenRouter
2. Navigate to Keys
3. Create a new key
4. Copy the key

Key Security

• Store Securely - Keys are encrypted in the database
• Don’t Share - Never share API keys
• Rotate Regularly - Update keys periodically
• Monitor Usage - Watch for unauthorized use

Cost Considerations

Predefined Models

• Costs are managed by Odin
• Billed through your Odin subscription
• Credits-based pricing
• Transparent pricing model

Custom Models (BYOK)

• You pay directly to the provider
• No additional Odin fees
• Full control over costs
• Direct billing from provider

Cost Optimization

• Choose Right Model - Use appropriate model for task
• Optimize Prompts - Reduce token usage
• Set Limits - Configure max tokens appropriately
• Monitor Usage - Track API usage regularly

Related Features

• Agent Configuration - Configure agent behavior
• Model Settings - Adjust temperature and other parameters
• Token Management - Monitor and optimize token usage
• Cost Tracking - Track model usage and costs

Agent Configuration

Learn how to configure your agents

Support

Need help with model configuration? Contact Support.