📊 Comprehensive Performance Report

{
  "report_metadata": {
    "generated_at": "2026-03-01T22:49:52.658952Z",
    "report_type": "comprehensive_performance_analysis",
    "platform": "InferenceLatency.com",
    "version": "1.0"
  },
  "latency_data": {
    "service": "InferenceLatency.com",
    "providers": [
      {
        "name": "Google Gemini",
        "model": "gemini-2.0-flash-exp",
        "latency_ms": null,
        "error": "All recent attempts failed",
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Groq",
        "model": "llama-3.1-8b-instant",
        "latency_ms": 372,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Fireworks AI",
        "model": "accounts/fireworks/models/llama-v3p1-8b-instruct",
        "latency_ms": null,
        "error": "All recent attempts failed",
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Cerebras",
        "model": "llama-4-scout-17b-16e-instruct",
        "latency_ms": null,
        "error": "All recent attempts failed",
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "OpenRouter",
        "model": "mistralai/mistral-7b-instruct",
        "latency_ms": null,
        "error": "All recent attempts failed",
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Together AI",
        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
        "latency_ms": 439,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "SambaNova",
        "model": "Meta-Llama-3.1-8B-Instruct",
        "latency_ms": 472,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Anthropic",
        "model": "claude-3-5-sonnet-20241022",
        "latency_ms": null,
        "error": "All recent attempts failed",
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Hyperbolic",
        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
        "latency_ms": 700,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "OpenAI",
        "model": "gpt-4o",
        "latency_ms": 1612,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "DeepSeek",
        "model": "deepseek-chat",
        "latency_ms": 1669,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Cohere",
        "model": "command-a-03-2025",
        "latency_ms": 753,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      }
    ],
    "ranked": [
      {
        "name": "Groq",
        "model": "llama-3.1-8b-instant",
        "latency_ms": 372,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Together AI",
        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
        "latency_ms": 439,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "SambaNova",
        "model": "Meta-Llama-3.1-8B-Instruct",
        "latency_ms": 472,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Hyperbolic",
        "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
        "latency_ms": 700,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "Cohere",
        "model": "command-a-03-2025",
        "latency_ms": 753,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "OpenAI",
        "model": "gpt-4o",
        "latency_ms": 1612,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      },
      {
        "name": "DeepSeek",
        "model": "deepseek-chat",
        "latency_ms": 1669,
        "tokens_generated": 1,
        "success_rate": 0,
        "measurements_count": 0
      }
    ],
    "fastest": "Groq",
    "total_tested": 12,
    "successful_tests": 7,
    "failed_tests": 5,
    "performance_summary": {
      "fastest_ms": 372,
      "slowest_ms": 1669,
      "average_ms": 860
    },
    "ai_agent_guidance": {
      "recommended_provider": "Groq",
      "use_case": "Choose 'fastest' provider for lowest latency API calls",
      "fallback_order": [
        "Groq",
        "Together AI",
        "SambaNova",
        "Hyperbolic",
        "Cohere",
        "OpenAI",
        "DeepSeek"
      ],
      "reliability_score": "7/12 providers responding"
    },
    "human_readable_summary": "🏆 Fastest: Groq (372ms - Good) | 📊 Range: 372-1669ms | 📈 Average: 860ms | ✅ 7/12 providers responding",
    "timestamp": "2026-03-01T22:49:52.658678Z"
  },
  "summary": {
    "total_providers_tested": 12,
    "fastest_provider": "Groq",
    "average_latency_ms": 860,
    "most_cost_effective": "Together AI",
    "most_environmentally_friendly": "Google Gemini",
    "highest_reliability": "OpenAI"
  }
}