Skip to main content
CORE supports multiple AI model providers. Set your provider and API key in your environment variables, then choose which models to use for chat and embeddings.

​
Configuration

Two environment variables control which provider and model CORE uses: 
CHAT_PROVIDER=openai       # openai | anthropic | google | azure | ollama
MODEL=gpt-5-2025-08-07     # model ID for the selected provider

​
OpenAI

Get your API key from platform.openai.com. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=sk-...
MODEL=gpt-5-2025-08-07
Chat models
Model IDLabelComplexity
gpt-5.2-2025-12-11GPT-5.2Medium
gpt-5-2025-08-07GPT-5Medium
gpt-5-mini-2025-08-07GPT-5 MiniLow
Embedding models
Model IDLabelDimensions
text-embedding-3-smallText Embedding 3 Small1536
text-embedding-3-largeText Embedding 3 Large3072
EMBEDDINGS_PROVIDER=openai
EMBEDDING_MODEL=text-embedding-3-small
EMBEDDING_MODEL_SIZE=1536
Optional: OpenAI-compatible proxy If you’re using a proxy or a service with an OpenAI-compatible API, set OPENAI_BASE_URL and OPENAI_API_MODE: 
OPENAI_BASE_URL=https://your-proxy.example.com/v1
OPENAI_API_MODE=chat_completions   # use chat_completions for most proxies

​
Anthropic

Get your API key from console.anthropic.com. 
CHAT_PROVIDER=anthropic
ANTHROPIC_API_KEY=sk-ant-...
MODEL=claude-sonnet-4-6
Chat models
Model IDLabelComplexity
claude-sonnet-4-6Claude Sonnet 4.6Medium
claude-haiku-4-5Claude Haiku 4.5Low

​
Google

Get your API key from aistudio.google.com. 
CHAT_PROVIDER=google
GOOGLE_GENERATIVE_AI_API_KEY=AIza...
MODEL=gemini-2.5-pro-preview-03-25
Chat models
Model IDLabelComplexity
gemini-2.5-pro-preview-03-25Gemini 2.5 ProMedium
gemini-2.5-flash-preview-04-17Gemini 2.5 FlashLow
Embedding models
Model IDLabelDimensions
text-embedding-004Text Embedding 004768
EMBEDDINGS_PROVIDER=google
EMBEDDING_MODEL=text-embedding-004
EMBEDDING_MODEL_SIZE=768

​
Azure OpenAI

Set up a deployment in the Azure portal, then configure: 
CHAT_PROVIDER=azure
AZURE_API_KEY=...
AZURE_BASE_URL=https://<your-resource>.openai.azure.com
MODEL=azure/gpt-4.1
Chat models
Model IDLabelComplexity
azure/gpt-4oGPT-4o (Azure)Medium
azure/gpt-4o-miniGPT-4o Mini (Azure)Low
azure/gpt-4.1GPT-4.1 (Azure)High

​
Ollama (Local)

Run models locally with Ollama. No API key required. 
CHAT_PROVIDER=ollama
OLLAMA_URL=http://ollama:11434
MODEL=llama3.2
Pull a model before starting CORE: 
ollama pull llama3.2
Ollama can also be used for embeddings and reranking: 
EMBEDDINGS_PROVIDER=ollama
EMBEDDING_MODEL=mxbai-embed-large
EMBEDDING_MODEL_SIZE=1024

RERANK_PROVIDER=ollama
OLLAMA_RERANK_MODEL=dengcao/Qwen3-Reranker-8B:Q5_K_M

​
OpenRouter

OpenRouter gives access to models from many providers through a single API. It uses an OpenAI-compatible interface. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=sk-or-...
OPENAI_BASE_URL=https://openrouter.ai/api/v1
OPENAI_API_MODE=chat_completions
MODEL=openrouter/anthropic/claude-3.5-sonnet

​
DeepSeek

Get your API key from platform.deepseek.com. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=sk-...
OPENAI_BASE_URL=https://api.deepseek.com/v1
OPENAI_API_MODE=chat_completions
MODEL=deepseek-chat
Models
Model IDDescription
deepseek-chatDeepSeek V3 — fast, general-purpose
deepseek-reasonerDeepSeek R1 — reasoning model

​
Groq

Get your API key from console.groq.com. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=gsk_...
OPENAI_BASE_URL=https://api.groq.com/openai/v1
OPENAI_API_MODE=chat_completions
MODEL=llama-3.3-70b-versatile
Models
Model IDDescription
llama-3.3-70b-versatileLlama 3.3 70B — fast, general-purpose
llama-3.1-8b-instantLlama 3.1 8B — ultra-fast
gemma2-9b-itGemma 2 9B

​
Mistral

Get your API key from console.mistral.ai. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=...
OPENAI_BASE_URL=https://api.mistral.ai/v1
OPENAI_API_MODE=chat_completions
MODEL=mistral-large-latest
Models
Model IDDescription
mistral-large-latestMistral Large — most capable
mistral-small-latestMistral Small — fast, cost-efficient

​
xAI (Grok)

Get your API key from console.x.ai. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=xai-...
OPENAI_BASE_URL=https://api.x.ai/v1
OPENAI_API_MODE=chat_completions
MODEL=grok-3
Models
Model IDDescription
grok-3Grok 3 — flagship model
grok-3-miniGrok 3 Mini — fast, lightweight

​
Kimi (Moonshot)

Get your API key from platform.moonshot.cn. 
CHAT_PROVIDER=openai
OPENAI_API_KEY=sk-...
OPENAI_BASE_URL=https://api.moonshot.cn/v1
OPENAI_API_MODE=chat_completions
MODEL=moonshot-v1-8k
Models
Model IDContextDescription
moonshot-v1-8k8KFast, short context
moonshot-v1-32k32KBalanced
moonshot-v1-128k128KLong context

​
Any OpenAI-compatible API

CORE can connect to any provider that exposes an OpenAI-compatible API (e.g. LM Studio, vLLM, Together AI, Fireworks, etc.): 
CHAT_PROVIDER=openai
OPENAI_API_KEY=<your-key>
OPENAI_BASE_URL=https://<provider-endpoint>/v1
OPENAI_API_MODE=chat_completions
MODEL=<model-id>