The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.
Install
npx skills add cheaper-inference/OmniRoute --skill omni-inferencenpx skills add cheaper-inference/OmniRoute --skill omni-inference -a claude-code -gnpx skills add cheaper-inference/OmniRoute --skill omni-inference -a codex -ggemini skills install https://github.com/cheaper-inference/OmniRoute.git --path skills/omni-inferencegh skill install cheaper-inference/OmniRoute omni-inferencegit clone --depth 1 https://github.com/cheaper-inference/OmniRoute /tmp/cheaper-inference__OmniRoute
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/cheaper-inference__OmniRoute/skills/omni-inference ~/.claude/skills/omni-inference # Claude Code
cp -R /tmp/cheaper-inference__OmniRoute/skills/omni-inference ~/.agents/skills/omni-inference # Codex, Cursor, Gemini CLI, Copilot, OpenCode