{"service":"InferenceLatency.com","providers":[{"name":"Google Gemini","model":"gemini-2.5-flash","latency_ms":6072,"tokens_generated":1,"success_rate":100.0,"measurements_count":1},{"name":"Groq","model":"llama-3.3-70b-versatile","latency_ms":734,"tokens_generated":1,"success_rate":100.0,"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":"Cerebras","model":"llama3.1-8b","latency_ms":429,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenRouter","model":"mistralai/mistral-small-3.2-24b-instruct","latency_ms":1064,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Nvidia NIM","model":"meta/llama-3.1-8b-instruct","latency_ms":566,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Hyperbolic","model":"meta-llama/Llama-3.3-70B-Instruct","latency_ms":1102,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Together AI","model":"meta-llama/Llama-3.3-70B-Instruct-Turbo","latency_ms":1066,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"DeepSeek","model":"deepseek-chat","latency_ms":1847,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Perplexity","model":"sonar","latency_ms":1267,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Anthropic","model":"claude-sonnet-4-5-20250929","latency_ms":2676,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenAI","model":"gpt-4o","latency_ms":1768,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Mistral AI","model":"mistral-small-latest","latency_ms":699,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Cohere","model":"command-a-03-2025","latency_ms":null,"error":"All recent attempts failed","success_rate":0.0,"measurements_count":2},{"name":"xAI (Grok)","model":"grok-3-mini-fast","latency_ms":7301,"tokens_generated":1,"success_rate":100.0,"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}],"ranked":[{"name":"Cerebras","model":"llama3.1-8b","latency_ms":429,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Nvidia NIM","model":"meta/llama-3.1-8b-instruct","latency_ms":566,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Mistral AI","model":"mistral-small-latest","latency_ms":699,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Groq","model":"llama-3.3-70b-versatile","latency_ms":734,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenRouter","model":"mistralai/mistral-small-3.2-24b-instruct","latency_ms":1064,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Together AI","model":"meta-llama/Llama-3.3-70B-Instruct-Turbo","latency_ms":1066,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Hyperbolic","model":"meta-llama/Llama-3.3-70B-Instruct","latency_ms":1102,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Perplexity","model":"sonar","latency_ms":1267,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"OpenAI","model":"gpt-4o","latency_ms":1768,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"DeepSeek","model":"deepseek-chat","latency_ms":1847,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Anthropic","model":"claude-sonnet-4-5-20250929","latency_ms":2676,"tokens_generated":1,"success_rate":100.0,"measurements_count":2},{"name":"Google Gemini","model":"gemini-2.5-flash","latency_ms":6072,"tokens_generated":1,"success_rate":100.0,"measurements_count":1},{"name":"xAI (Grok)","model":"grok-3-mini-fast","latency_ms":7301,"tokens_generated":1,"success_rate":100.0,"measurements_count":2}],"fastest":"Cerebras","total_tested":16,"successful_tests":13,"failed_tests":3,"performance_summary":{"fastest_ms":429,"slowest_ms":7301,"average_ms":2045},"ai_agent_guidance":{"recommended_provider":"Cerebras","use_case":"Choose 'fastest' provider for lowest latency API calls","fallback_order":["Cerebras","Nvidia NIM","Mistral AI","Groq","OpenRouter","Together AI","Hyperbolic","Perplexity","OpenAI","DeepSeek","Anthropic","Google Gemini","xAI (Grok)"],"reliability_score":"13/16 providers responding"},"human_readable_summary":"🏆 Fastest: Cerebras (429ms - Good) | 📊 Range: 429-7301ms | 📈 Average: 2045ms | ✅ 13/16 providers responding","timestamp":"2026-04-16T01:06:05.864928Z"}