{"service":"InferenceLatency.com","providers":[{"name":"Google Gemini","model":"gemini-2.5-flash","latency_ms":4149,"tokens_generated":1,"success_rate":100.0,"measurements_count":1},{"name":"Groq","model":"llama-3.3-70b-versatile","latency_ms":483,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Cerebras","model":"llama3.1-8b","latency_ms":null,"error":"All recent attempts failed","success_rate":0.0,"measurements_count":2},{"name":"Fireworks AI","model":"accounts/fireworks/models/deepseek-v3p2","latency_ms":null,"error":"All recent attempts failed","success_rate":0.0,"measurements_count":2},{"name":"Perplexity","model":"sonar","latency_ms":null,"error":"All recent attempts failed","success_rate":0.0,"measurements_count":2},{"name":"SambaNova","model":"Meta-Llama-3.1-8B-Instruct","latency_ms":null,"error":"All recent attempts failed","success_rate":0.0,"measurements_count":2},{"name":"OpenRouter","model":"mistralai/mistral-small-3.2-24b-instruct","latency_ms":737,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Mistral AI","model":"mistral-small-latest","latency_ms":1095,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"DeepSeek","model":"deepseek-chat","latency_ms":1371,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Cohere","model":"command-a-03-2025","latency_ms":649,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Nvidia NIM","model":"meta/llama-3.1-8b-instruct","latency_ms":676,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Hyperbolic","model":"meta-llama/Llama-3.3-70B-Instruct","latency_ms":5284,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenAI","model":"gpt-4o","latency_ms":1240,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Together AI","model":"meta-llama/Llama-3.3-70B-Instruct-Turbo","latency_ms":894,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Anthropic","model":"claude-sonnet-4-5-20250929","latency_ms":1846,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"xAI (Grok)","model":"grok-3-mini-fast","latency_ms":3357,"tokens_generated":1,"success_rate":100.0,"measurements_count":2}],"ranked":[{"name":"Groq","model":"llama-3.3-70b-versatile","latency_ms":483,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Cohere","model":"command-a-03-2025","latency_ms":649,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Nvidia NIM","model":"meta/llama-3.1-8b-instruct","latency_ms":676,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenRouter","model":"mistralai/mistral-small-3.2-24b-instruct","latency_ms":737,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Together AI","model":"meta-llama/Llama-3.3-70B-Instruct-Turbo","latency_ms":894,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Mistral AI","model":"mistral-small-latest","latency_ms":1095,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenAI","model":"gpt-4o","latency_ms":1240,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"DeepSeek","model":"deepseek-chat","latency_ms":1371,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Anthropic","model":"claude-sonnet-4-5-20250929","latency_ms":1846,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"xAI (Grok)","model":"grok-3-mini-fast","latency_ms":3357,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Google Gemini","model":"gemini-2.5-flash","latency_ms":4149,"tokens_generated":1,"success_rate":100.0,"measurements_count":1},{"name":"Hyperbolic","model":"meta-llama/Llama-3.3-70B-Instruct","latency_ms":5284,"tokens_generated":1,"success_rate":100.0,"measurements_count":2}],"fastest":"Groq","total_tested":16,"successful_tests":12,"failed_tests":4,"performance_summary":{"fastest_ms":483,"slowest_ms":5284,"average_ms":1815},"ai_agent_guidance":{"recommended_provider":"Groq","use_case":"Choose 'fastest' provider for lowest latency API calls","fallback_order":["Groq","Cohere","Nvidia NIM","OpenRouter","Together AI","Mistral AI","OpenAI","DeepSeek","Anthropic","xAI (Grok)","Google Gemini","Hyperbolic"],"reliability_score":"12/16 providers responding"},"human_readable_summary":"🏆 Fastest: Groq (483ms - Good) | 📊 Range: 483-5284ms | 📈 Average: 1815ms | ✅ 12/16 providers responding","timestamp":"2026-05-31T17:24:32.739736Z"}