Terminal
Terminal/Skill
Shows how to set model handles, temperature, and token limits on Letta agents, and how to add model provider keys to a server.
By Letta
Works with
npx skills add letta-ai/skills --skill letta-configurationComplete guide for configuring models on agents and providers on servers.
Agent-level (model configuration):
Server-level (provider configuration):
Not covered here: Model selection advice (which model to choose) - see agent-development skill.
Models use a provider/model-name format:
| Provider | Handle Prefix | Example |
|---|---|---|
| OpenAI | openai/ | openai/gpt-4o, openai/gpt-4o-mini |
| Anthropic | anthropic/ | anthropic/claude-sonnet-4-5-20250929 |
| Google AI | google_ai/ | google_ai/gemini-2.0-flash |
| Azure OpenAI | azure/ | azure/gpt-4o |
| AWS Bedrock | bedrock/ | bedrock/anthropic.claude-3-5-sonnet |
| Groq | groq/ | groq/llama-3.3-70b-versatile |
| Together | together/ | together/meta-llama/Llama-3-70b |
| OpenRouter | openrouter/ | openrouter/anthropic/claude-3.5-sonnet |
| Ollama (local) | ollama/ | ollama/llama3.2 |
from letta_client import Letta
client = Letta(api_key="your-api-key")
agent = client.agents.create(
model="openai/gpt-4o",
model_settings={
"provider_type": "openai", # Required - must match model provider
"temperature": 0.7,
"max_output_tokens": 4096,
},
context_window_limit=128000
)
| Setting | Type | Description |
|---|---|---|
provider_type | string | Required. Must match model provider (openai, anthropic, google_ai, etc.) |
temperature | float | Controls randomness (0.0-2.0). Lower = more deterministic. |
max_output_tokens | int | Maximum tokens in the response. |
client.agents.update(
agent_id=agent.id,
model="anthropic/claude-sonnet-4-5-20250929",
model_settings={"provider_type": "anthropic", "temperature": 0.5},
context_window_limit=64000
)
Note: Agents retain memory and tools when changing models.
For OpenAI reasoning models and Anthropic extended thinking, see references/provider-settings.md.
# Add provider via API
python scripts/setup_provider.py --type openai --api-key sk-...
# Generate .env for Docker
python scripts/generate_env.py --providers openai,anthropic,ollama
# Validate credentials
python scripts/validate_provider.py --provider-id provider-xxx
# Via REST API
curl -X POST http://localhost:8283/v1/providers \
-H "Content-Type: application/json" \
-d '{
"name": "My OpenAI",
"provider_type": "openai",
"api_key": "sk-your-key-here"
}'
openai, anthropic, azure, google_ai, google_vertex, ollama, groq, deepseek, xai, together, mistral, cerebras, bedrock, vllm, sglang, hugging_face, lmstudio_openai
For detailed configuration of each provider, see:
references/common_providers.md - OpenAI, Anthropic, Azure, Googlereferences/self_hosted_providers.md - Ollama, vLLM, LM Studioreferences/all_providers.md - Complete referencereferences/environment_variables.md - Docker/self-hosted setupBefore configuring:
provider/model-name formatmodel_settings includes required provider_type fieldcontext_window_limit is set at agent level, not in model_settingsModel configuration:
scripts/basic_config.py - Basic model configurationscripts/basic_config.ts - TypeScript equivalentscripts/change_model.py - Changing models on existing agentsscripts/provider_specific.py - OpenAI reasoning, Anthropic thinkingProvider configuration:
scripts/setup_provider.py - Add providers via REST APIscripts/validate_provider.py - Check provider credentialsscripts/generate_env.py - Generate .env for Docker