Letta Model Configuration

Patterns for configuring LLM models on Letta agents via SDK/API. Covers model handles, settings, provider-specific configuration, and custom endpoints.

When to Use This Skill

Use this skill when:

• Creating agents with specific model configurations
• Adjusting model settings (temperature, max tokens, context window)
• Configuring provider-specific features (OpenAI reasoning, Anthropic thinking)
• Setting up custom OpenAI-compatible endpoints
• Changing models on existing agents
• Configuring embedding models for self-hosted deployments

Not covered here: Model selection advice (which model to choose) - see agent-development skill's references/model-recommendations.md.

Model Handles

Models use a provider/model-name format: