Providers

Astreus CLI supports multiple LLM providers. Switch between them seamlessly to test your agents with different models and find the best fit for your use case.

Supported Providers

OpenAI

The default provider with access to GPT models.

export OPENAI_API_KEY=sk-your-api-key
astreus

Available Models:

gpt-4o (default) - Most capable
gpt-4o-mini - Fast and efficient
gpt-4-turbo - GPT-4 Turbo
gpt-4 - Original GPT-4
gpt-3.5-turbo - Fast and cost-effective

Anthropic (Claude)

Access Claude models for nuanced conversations.

export ANTHROPIC_API_KEY=your-api-key
ASTREUS_PROVIDER=claude astreus

Available Models:

claude-sonnet-4-20250514 (default) - Claude Sonnet 4
claude-3-5-sonnet-20241022 - Claude 3.5 Sonnet

Google (Gemini)

Use Google's Gemini models.

export GEMINI_API_KEY=your-api-key
ASTREUS_PROVIDER=gemini astreus

Available Models:

gemini-pro (default) - Gemini Pro
gemini-pro-vision - Vision capable

Ollama (Local Models)

Run models locally with Ollama. No API key required.

# Make sure Ollama is running
ollama serve

# Start CLI with Ollama
ASTREUS_PROVIDER=ollama astreus

Available Models:

llama3 (default) - Llama 3
llama2 - Llama 2
mistral - Mistral
codellama - Code-focused Llama

Switching Providers

At Startup

Use environment variables:

ASTREUS_PROVIDER=claude ASTREUS_MODEL=claude-sonnet-4-20250514 astreus

During Session

Use slash commands to switch:

/provider claude
/model claude-sonnet-4-20250514

Or open the interactive selector:

/provider
/model

Provider Configuration

Custom Endpoints

For enterprise deployments or proxies:

# Ollama on different host
export OLLAMA_HOST=http://192.168.1.100:11434

Vision Support

Some providers support vision (image) capabilities:

# Separate API key for vision (optional)
export OPENAI_VISION_API_KEY=sk-your-vision-key
export ANTHROPIC_VISION_API_KEY=your-vision-key
export GEMINI_VISION_API_KEY=your-vision-key

Embedding Support

For memory and knowledge features:

export OPENAI_EMBEDDING_API_KEY=sk-your-embedding-key
export GEMINI_EMBEDDING_API_KEY=your-embedding-key

Model Selection for Agent Development

Choose the right model based on the type of agent you're building:

Agent Type	Recommended Model	Why
Code Analysis Agent	`claude-sonnet-4-20250514`	Excellent at understanding code structure and patterns
Complex Reasoning Agent	`gpt-4o`, `claude-sonnet-4-20250514`	Best for multi-step reasoning and planning
Fast Response Agent	`gpt-4o-mini`, `gemini-pro`	Low latency for real-time interactions
Tool-Heavy Agent	`gpt-4o`	Reliable function calling and tool use
Long Context Agent	`claude-sonnet-4-20250514`	200k context window for large documents
Local/Private Agent	`llama3`, `codellama`	No data leaves your machine
Cost-Sensitive Agent	`gpt-3.5-turbo`, Ollama	Minimize API costs

Testing Agents Across Providers

When building agents, it's useful to test with different providers:

# Start developing with fast, cheap model
/provider openai
/model gpt-4o-mini

# Test complex reasoning with top models
/provider claude
/model claude-sonnet-4-20250514

# Test locally before deployment
/provider ollama
/model llama3

This workflow helps you understand how your agent performs across different LLMs and find the best balance of capability, speed, and cost for your use case.

Last updated: May 26, 2026

Commands

Configuration