{"name":"Impala AI Documentation","url":"https://docs.getimpala.ai/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.getimpala.ai/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.getimpala.ai/","organization":"Impala AI Documentation"},"documentationUrl":"https://docs.getimpala.ai/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"impalaai","name":"Impalaai","description":"Use when building async inference workloads, batch processing pipelines, agent orchestration systems, or cost-optimized inference for open-source models. Reach for this skill when you need to run high-volume inference at the lowest cost per token, whether through serverless endpoints or bring-your-own-cloud deployments.","tags":[],"url":"https://docs.getimpala.ai/.well-known/agent-skills/impalaai/skill.md"}]}