{"name":"InferenceLatency","description":"Real-time AI inference routing and benchmarking across 15 providers. Returns latency, cost, reliability, and routing recommendations on-demand. No auth required.","url":"https://inferencelatency.com/","version":"1.0","documentationUrl":"https://inferencelatency.com/docs","provider":{"organization":"InferenceLatency.com","url":"https://inferencelatency.com"},"capabilities":{"streaming":false,"pushNotifications":false,"stateTransitionHistory":false},"authentication":{"schemes":[]},"defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["application/json"],"skills":[{"id":"route-fastest","name":"Route to Fastest Provider","description":"Returns the lowest-latency AI inference provider right now. Optionally filter by priority (speed/cost/balanced/reliability) and use_case (chat/code/reasoning).","tags":["routing","latency","inference"],"examples":["Which AI provider is fastest right now?","Route my request to the lowest-latency provider","Find the fastest provider for code generation"],"inputModes":["text/plain"],"outputModes":["application/json"]},{"id":"recommend-provider","name":"Recommend Provider by Natural Language","description":"Accepts a plain-English description of your needs and returns ranked providers with live test results and reasoning.","tags":["routing","recommendation","natural-language"],"examples":["What's the cheapest provider for code generation?","I need a reliable provider for real-time chat","Which provider has the best reliability?"],"inputModes":["text/plain"],"outputModes":["application/json"]},{"id":"benchmark-providers","name":"Benchmark All Providers","description":"Tests all 15 providers with your prompt and returns ranked latency results.","tags":["benchmark","comparison"],"examples":["Benchmark all providers with my prompt","Compare provider speeds for this task"],"inputModes":["text/plain","application/json"],"outputModes":["application/json"]},{"id":"cost-analysis","name":"Cost-Performance Analysis","description":"Returns efficiency scores combining cost per token and latency for all providers.","tags":["cost","efficiency"],"examples":["Which provider gives the best value for money?","Find the most cost-efficient provider"],"inputModes":["text/plain"],"outputModes":["application/json"]},{"id":"reliability-metrics","name":"Reliability Metrics","description":"Returns P50/P95/P99 latency percentiles, error rates, and SLA compliance for all providers.","tags":["reliability","sla","uptime"],"examples":["Which provider has the best SLA compliance?","Show reliability statistics for all providers"],"inputModes":["text/plain"],"outputModes":["application/json"]},{"id":"geographic-latency","name":"Geographic Latency Analysis","description":"Returns estimated latency per provider across 5 continents.","tags":["geographic","latency","regional"],"examples":["Which provider is fastest in Europe?","Show latency by region"],"inputModes":["text/plain"],"outputModes":["application/json"]}]}