{"name":"Pareto Inference","description":"GLM 5.3 Flash on Pareto GPUs. Pay per token. Connect through a router or call the API directly.","url":"https://docs.paretoinference.com/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.paretoinference.com/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.paretoinference.com/","organization":"Pareto Inference"},"documentationUrl":"https://docs.paretoinference.com/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"pareto","name":"pareto","description":"Use when integrating GLM 5.3 Flash inference into applications, routing requests through LLM gateways, connecting coding agents or chat applications to a cost-effective model API, or managing API keys and prepaid credits for token-based inference.","tags":[],"url":"https://docs.paretoinference.com/.well-known/agent-skills/pareto/skill.md"}]}