Models
Configure and manage AI models for your agents, tools, and workflows.Overview
Agent Platform is model-agnostic, supporting a wide range of AI models from commercial providers, open-source repositories, and custom fine-tuned deployments. Access Model Hub from the top navigation to manage all your models in one place. Model Hub provides three ways to work with models:| Model Type | Description | Best For |
|---|---|---|
| External Models | Commercial models from OpenAI, Anthropic, Google, Azure, Cohere, and Amazon Bedrock | Production workloads requiring proven reliability |
| Open-Source Models | 30+ curated models plus any Hugging Face text generation model | Cost control, customization, data privacy |
| Fine-Tuned Models | Custom models trained on your enterprise data | Domain-specific tasks, consistent outputs |
External Models
Connect commercial models with minimal setup using Easy Integration or API Integration.Supported Providers
| Provider | Popular Models | Tool Calling |
|---|---|---|
| OpenAI | GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo, o1 series | ✓ |
| Anthropic | Claude 3.5 Sonnet, Claude 3 Opus/Sonnet/Haiku | ✓ |
| Gemini 1.5 Pro, Gemini 1.5 Flash | ✓ | |
| Azure OpenAI | GPT-4o, GPT-4, GPT-3.5 Turbo | ✓ |
| Cohere | Command R+, Command R | ✓ |
| Amazon Bedrock | Claude, Titan, Llama models via AWS | ✓ |
Adding an External Model
Easy Integration (recommended):- Go to Models → External Models → Add a model
- Select Easy Integration and choose your provider
- Enter your API credentials
- Select the model and confirm
- Select API Integration when adding a model
- Configure the endpoint URL and authentication
- Map request/response parameters
- Test and save
Note: Custom models must support tool calling and follow OpenAI or Anthropic API structures to work with Agentic Apps.For detailed setup instructions, see Add a Model using Easy Integration or Add a Model using API Integration.
Open-Source Models
Deploy from 30+ curated models or import any text generation model from Hugging Face.Deployment Options
| Option | Description |
|---|---|
| Kore-Hosted | Select from curated models, optimize, and deploy on managed infrastructure |
| Hugging Face Import | Bring any compatible model from Hugging Face (public or private) |
Optimization Techniques
Before deployment, optimize models for better performance:- vLLM: High-throughput inference optimization
- CTranslate2 (CT2): Efficient inference with reduced memory footprint
- No Optimization: Deploy as-is for maximum compatibility
Quick Deploy Steps
- Go to Models → Open-source models → Deploy a model
- Select a Kore-hosted model or import from Hugging Face
- Choose optimization technique (optional)
- Configure parameters and hardware
- Click Deploy
Fine-Tuned Models
Create custom models trained on your enterprise data for domain-specific tasks.When to Fine-Tune
- Consistent output format required across responses
- Domain-specific terminology or jargon
- Unique tone, style, or brand voice
- Improved accuracy for specialized tasks
Fine-Tuning Process
- Prepare Data: Format training data as JSONL with conversation examples
- Select Base Model: Choose from supported Kore-hosted or Hugging Face models
- Configure Training: Select fine-tuning type (Full, LoRA, or QLoRA)
- Monitor Progress: Track metrics via Weights & Biases integration
- Deploy: Make the model available across Agent Platform
Training Data Format
Model Parameters
Configure generation behavior when using models across Agent Platform:| Parameter | Description | Typical Range |
|---|---|---|
| Temperature | Controls randomness. Lower = focused, higher = creative | 0.0–2.0 (default: 0.7) |
| Top P | Nucleus sampling—considers tokens within probability mass | 0.0–1.0 (default: 0.9) |
| Top K | Limits selection to top K tokens | 1–100 (default: 50) |
| Max Tokens | Maximum output length | Varies by model |
| Stop Sequences | Strings that stop generation | Custom list |
Tool Calling Support
Not all models support tool calling, which is required for Agentic Apps. Use models with tool calling support for agent orchestration. Supported for Tool Calling:- OpenAI: GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo
- Anthropic: Claude 3.5 Sonnet, Claude 3 series
- Google: Gemini 1.5 Pro, Gemini 1.5 Flash
- Azure OpenAI: GPT-4o, GPT-4, GPT-3.5 Turbo
- Amazon Bedrock: Models via supported providers
- Kore-hosted open-source models
- Most Hugging Face imports
- Models without function calling capabilities
Model Selection Guide
Choose the right model based on your use case:| Use Case | Recommended Models | Why |
|---|---|---|
| Complex reasoning | GPT-4o, Claude 3 Opus | Highest accuracy |
| Fast responses | GPT-3.5, Claude 3 Haiku, Gemini Flash | Low latency |
| Code generation | GPT-4o, Claude 3.5 Sonnet | Best code quality |
| Cost-sensitive | GPT-3.5, Claude 3 Haiku | Lower token cost |
| Long context | Claude 3, Gemini 1.5 | 100K+ token windows |
| Data privacy | Open-source (Kore-hosted) | No external API calls |
| Real-time voice | GPT-4o Realtime Preview | Native voice support |
Structured Output
Enable consistent, parseable responses using JSON schemas. Supported:- External models (OpenAI, Anthropic, Google)
- Kore-hosted open-source models with vLLM or no optimization
- CT2-optimized models
- Fine-tuned models
- Hugging Face imports
- Locally imported models
Model Endpoint & API Keys
After deployment, each model provides:- API Endpoint: Use models externally via REST API
- API Keys: Secure access tokens for endpoint authentication
- Deployment History: Track version changes
Monitoring
Track model performance across Agent Platform:- Model Analytics Dashboard: Token usage, latency, error rates
- Model Traces: Detailed request/response logs
- Usage Summary: Cost tracking by model
Related
- Supported Models — Complete list of all supported models
- Prompt Studio — Create and test prompts with different models
- AI Nodes — Use models in workflow tools
- Model Analytics — Monitor model performance