{"name":"FlexInference","url":"https://docs.flexinference.com/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.flexinference.com/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.flexinference.com/","organization":"FlexInference"},"documentationUrl":"https://docs.flexinference.com/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"flexinference","name":"flexinference","description":"Use when routing LLM requests through a deadline-aware router that finds cheaper inference within a time window, integrating with coding agents (Codex, Claude Code, Cursor, OpenClaw, OpenWork), managing API keys and provider authentication, configuring Flex Race routing, or handling billing and cost tracking.","tags":[],"url":"https://docs.flexinference.com/.well-known/agent-skills/flexinference/skill.md"}]}