{"schema_version":"v1","name_for_model":"inferencelatency","name_for_human":"InferenceLatency.com","description_for_model":"Real-time AI inference latency, throughput, cost, and reliability monitoring across 15 active providers: OpenAI, Anthropic, Groq, OpenRouter, Google Gemini, DeepSeek, Cohere, Together AI, Fireworks AI, Cerebras, SambaNova, xAI (Grok), Mistral AI, Perplexity, Nvidia NIM. Use /v1/should-call before inference to get a complete routing decision. Use /api/fastest to get the lowest-latency provider right now. Use /latency for full ranked results. Use /cost-optimizer for price-performance efficiency. Use /reliability-metrics for P95/P99 SLA data. Use /benchmark?prompt=X&max_tokens=N to test a specific prompt. All endpoints return JSON. No authentication required. MCP server also available at https://inferencelatency.com/mcp (SSE transport).","description_for_human":"Free public API: compare AI inference speed, cost, and reliability across 15 active providers. No auth. MCP-enabled.","api":{"type":"openapi","url":"https://inferencelatency.com/openapi.json","is_user_authenticated":false},"auth":{"type":"none"},"logo_url":"https://inferencelatency.com/favicon.svg","contact_email":"contact@inferencedomains.com","legal_info_url":"https://inferencelatency.com/","homepage_url":"https://inferencelatency.com/","capabilities":["real_time_latency_monitoring","provider_performance_ranking","cost_optimization","reliability_metrics","geographic_latency_analysis","custom_prompt_benchmarking","mcp_tool_server","no_authentication_required"]}