Skip to main content
Strix uses LiteLLM for model compatibility, supporting 100+ LLM providers. The fastest way to get started. Strix Router gives you access to tested models with the highest rate limits and zero data retention. 
export STRIX_LLM="strix/gpt-5"
export LLM_API_KEY="your-strix-api-key"
Get your API key at models.strix.ai.

​
Bring Your Own Key

You can also use any LiteLLM-compatible provider with your own API keys:
ModelProviderConfiguration
GPT-5OpenAIopenai/gpt-5
Claude Sonnet 4.6Anthropicanthropic/claude-sonnet-4-6
Gemini 3 ProGoogle Vertexvertex_ai/gemini-3-pro-preview
export STRIX_LLM="openai/gpt-5"
export LLM_API_KEY="your-api-key"

​
Local Models

Run models locally with Ollama, LM Studio, or any OpenAI-compatible server: 
export STRIX_LLM="ollama/llama4"
export LLM_API_BASE="http://localhost:11434"
See the Local Models guide for setup instructions and recommended models.

​
Provider Guides

Strix Router

Recommended models router with high rate limits.

OpenAI

GPT-5 and Codex models.

Anthropic

Claude Opus, Sonnet, and Haiku.

OpenRouter

Access 100+ models through a single API.

Google Vertex AI

Gemini 3 models via Google Cloud.

AWS Bedrock

Claude and Titan models via AWS.

Azure OpenAI

GPT-5 via Azure.

Local Models

Llama 4, Mistral, and self-hosted models.

​
Model Format

Use LiteLLM’s provider/model-name format: 
openai/gpt-5
anthropic/claude-sonnet-4-6
vertex_ai/gemini-3-pro-preview
bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0
ollama/llama4