AI inference router that runs models locally or routes requests to the cheapest capable provider on the Pareto frontier.
Conifer is a local AI runtime and router that routes LLM requests to the most cost-effective model for the task at hand. It works with cloud providers (OpenAI, Anthropic, OpenRouter), self-hosted models, and local hardware, supports hundreds of vendors, and charges no fee for bringing your own API keys or running on your own hardware. Compatible with Claude Desktop, Codex, VS Code, Cursor, and other AI environments, it provides visibility into token costs across all inference sources. Conifer is a product of Conifer.