{
  "schema_version": "1.0.0",
  "generated_at": "2026-11-16T15:25:35.773316+00:00",
  "source": "AI FinOps Cost Oracle Automated Multi-Cloud Engine",
  "base_currency": "USD",
  "eur_usd_rate": 1.08,
  "models": {
    "anthropic/claude-3-7-sonnet": {
      "provider": "Anthropic",
      "model_name": "Claude 3.7 Sonnet (Hybrid Reasoning)",
      "input_cost_per_token": 3e-06,
      "output_cost_per_token": 1.5e-05,
      "input_cost_per_million": 3.0,
      "output_cost_per_million": 15.0,
      "context_window": 200000,
      "max_output_tokens": 64000,
      "category": "frontier_hybrid",
      "description": "Anthropic frontier hybrid reasoning model combining instant execution with controllable extended thinking tokens.",
      "last_synced_from": "LiteLLM-Live"
    },
    "openai/o3-mini": {
      "provider": "OpenAI",
      "model_name": "OpenAI o3-mini",
      "input_cost_per_token": 1.1e-06,
      "output_cost_per_token": 4.4e-06,
      "input_cost_per_million": 1.1,
      "output_cost_per_million": 4.4,
      "context_window": 200000,
      "max_output_tokens": 100000,
      "category": "reasoning_ultra",
      "description": "Next-gen high-efficiency STEM and coding reasoning model replacing o1-mini at lower cost and higher speed.",
      "last_synced_from": "LiteLLM-Live"
    },
    "openai/o3": {
      "provider": "OpenAI",
      "model_name": "OpenAI o3",
      "input_cost_per_token": 2e-06,
      "output_cost_per_token": 8e-06,
      "input_cost_per_million": 2.0,
      "output_cost_per_million": 8.0,
      "context_window": 200000,
      "max_output_tokens": 100000,
      "category": "reasoning_frontier",
      "description": "State-of-the-art general reasoning model superseding o1-preview with superior agentic performance.",
      "last_synced_from": "LiteLLM-Live"
    },
    "openai/gpt-4-5": {
      "provider": "OpenAI",
      "model_name": "GPT-4.5 (Super-Scale Knowledge)",
      "input_cost_per_token": 7.5e-05,
      "output_cost_per_token": 0.00015,
      "input_cost_per_million": 75.0,
      "output_cost_per_million": 150.0,
      "context_window": 128000,
      "max_output_tokens": 16384,
      "category": "massive_knowledge",
      "description": "Colossal world knowledge and nuanced qualitative synthesis model for mission-critical enterprise decisions."
    },
    "google/gemini-2-0-flash": {
      "provider": "Google",
      "model_name": "Gemini 2.0 Flash",
      "input_cost_per_token": 1e-07,
      "output_cost_per_token": 4e-07,
      "input_cost_per_million": 0.1,
      "output_cost_per_million": 0.4,
      "context_window": 1048576,
      "max_output_tokens": 8192,
      "category": "cost_optimized",
      "description": "Second-generation multimodal foundation model with native tool execution and sub-second latency."
    },
    "google/gemini-2-5-pro": {
      "provider": "Google",
      "model_name": "Gemini 2.5 Pro",
      "input_cost_per_token": 1.25e-06,
      "output_cost_per_token": 1e-05,
      "input_cost_per_million": 1.25,
      "output_cost_per_million": 10.0,
      "context_window": 1048576,
      "max_output_tokens": 16384,
      "category": "flagship",
      "description": "Advanced multi-modal reasoning with 2M token context, agentic planning, and codebase ingestion.",
      "last_synced_from": "LiteLLM-Live"
    },
    "deepseek/deepseek-reasoner": {
      "provider": "DeepSeek",
      "model_name": "DeepSeek R1 (Reasoner)",
      "input_cost_per_token": 2.8e-07,
      "output_cost_per_token": 4.2e-07,
      "input_cost_per_million": 0.28,
      "output_cost_per_million": 0.42,
      "context_window": 131072,
      "max_output_tokens": 8192,
      "category": "reasoning_open",
      "description": "Groundbreaking open reasoning model matching proprietary frontier reasoning at 90-96% lower cost.",
      "last_synced_from": "LiteLLM-Live"
    },
    "deepseek/deepseek-chat": {
      "provider": "DeepSeek",
      "model_name": "DeepSeek V3 (Chat)",
      "input_cost_per_token": 2.8e-07,
      "output_cost_per_token": 4.2e-07,
      "input_cost_per_million": 0.28,
      "output_cost_per_million": 0.42,
      "context_window": 131072,
      "max_output_tokens": 8192,
      "category": "hyper_efficient",
      "description": "671B MoE architecture delivering frontier coding and general reasoning at ultra-low price.",
      "last_synced_from": "LiteLLM-Live"
    },
    "openai/gpt-4o": {
      "provider": "OpenAI",
      "model_name": "GPT-4o (Omni)",
      "input_cost_per_token": 2.5e-06,
      "output_cost_per_token": 1e-05,
      "input_cost_per_million": 2.5,
      "output_cost_per_million": 10.0,
      "context_window": 128000,
      "max_output_tokens": 16384,
      "category": "flagship",
      "description": "OpenAI general multimodal workhorse model.",
      "last_synced_from": "LiteLLM-Live"
    },
    "openai/gpt-4o-mini": {
      "provider": "OpenAI",
      "model_name": "GPT-4o Mini",
      "input_cost_per_token": 1.5e-07,
      "output_cost_per_token": 6e-07,
      "input_cost_per_million": 0.15,
      "output_cost_per_million": 0.6,
      "context_window": 128000,
      "max_output_tokens": 16384,
      "category": "cost_optimized",
      "description": "Fast, economical multimodal model for high-frequency routing.",
      "last_synced_from": "LiteLLM-Live"
    },
    "anthropic/claude-3-5-sonnet": {
      "provider": "Anthropic",
      "model_name": "Claude 3.5 Sonnet",
      "input_cost_per_token": 3e-06,
      "output_cost_per_token": 1.5e-05,
      "input_cost_per_million": 3.0,
      "output_cost_per_million": 15.0,
      "context_window": 200000,
      "max_output_tokens": 8192,
      "category": "flagship",
      "description": "High capability programming and reasoning predecessor to Claude 3.7."
    },
    "anthropic/claude-3-5-haiku": {
      "provider": "Anthropic",
      "model_name": "Claude 3.5 Haiku",
      "input_cost_per_token": 1e-06,
      "output_cost_per_token": 5e-06,
      "input_cost_per_million": 1.0,
      "output_cost_per_million": 5.0,
      "context_window": 200000,
      "max_output_tokens": 8192,
      "category": "cost_optimized",
      "description": "Sub-second lightweight execution from Anthropic."
    },
    "mistral/mistral-large": {
      "provider": "Mistral AI",
      "model_name": "Mistral Large 2",
      "input_cost_per_token": 2e-06,
      "output_cost_per_token": 6e-06,
      "input_cost_per_million": 2.0,
      "output_cost_per_million": 6.0,
      "context_window": 128000,
      "max_output_tokens": 8192,
      "category": "flagship",
      "description": "European sovereign enterprise frontier model."
    },
    "mistral/codestral": {
      "provider": "Mistral AI",
      "model_name": "Codestral 25.01",
      "input_cost_per_token": 2e-07,
      "output_cost_per_token": 6e-07,
      "input_cost_per_million": 0.2,
      "output_cost_per_million": 0.6,
      "context_window": 256000,
      "max_output_tokens": 8192,
      "category": "code_specialist",
      "description": "Specialized generative coding and fill-in-the-middle completion model with 256k context."
    },
    "meta/llama-3.3-70b-instruct": {
      "provider": "Meta (via Groq / Together / DeepInfra)",
      "model_name": "Llama 3.3 70B Instruct",
      "input_cost_per_token": 5.9e-07,
      "output_cost_per_token": 7.9e-07,
      "input_cost_per_million": 0.59,
      "output_cost_per_million": 0.79,
      "context_window": 128000,
      "max_output_tokens": 4096,
      "category": "open_source_cloud",
      "description": "Open weights standard flagship model with near-405B benchmark parity."
    }
  },
  "automation_platforms": {
    "zapier": {
      "name": "Zapier (Cloud SaaS)",
      "billing_model": "per_task_tiered",
      "free_tier_ops": 100,
      "plans": [
        {
          "name": "Free",
          "monthly_price_usd": 0,
          "included_ops": 100,
          "overage_per_1000": 0
        },
        {
          "name": "Starter",
          "monthly_price_usd": 29.99,
          "included_ops": 750,
          "overage_per_1000": 45.0
        },
        {
          "name": "Professional",
          "monthly_price_usd": 73.5,
          "included_ops": 2000,
          "overage_per_1000": 38.0
        },
        {
          "name": "Team",
          "monthly_price_usd": 103.5,
          "included_ops": 2000,
          "overage_per_1000": 34.0
        },
        {
          "name": "High Volume 50k",
          "monthly_price_usd": 448.5,
          "included_ops": 50000,
          "overage_per_1000": 15.0
        },
        {
          "name": "Enterprise 100k",
          "monthly_price_usd": 898.0,
          "included_ops": 100000,
          "overage_per_1000": 12.0
        }
      ],
      "average_cost_per_task_usd": 0.038,
      "notes": "Premium proprietary pricing. Steep penalties on multi-step workflows where each step counts as 1 task."
    },
    "make": {
      "name": "Make (formerly Integromat)",
      "billing_model": "per_operation_tiered",
      "free_tier_ops": 1000,
      "plans": [
        {
          "name": "Free",
          "monthly_price_usd": 0,
          "included_ops": 1000,
          "overage_per_1000": 0
        },
        {
          "name": "Core",
          "monthly_price_usd": 10.59,
          "included_ops": 10000,
          "overage_per_1000": 1.2
        },
        {
          "name": "Pro",
          "monthly_price_usd": 18.82,
          "included_ops": 10000,
          "overage_per_1000": 1.8
        },
        {
          "name": "Teams",
          "monthly_price_usd": 34.12,
          "included_ops": 10000,
          "overage_per_1000": 3.4
        },
        {
          "name": "Pro 50k",
          "monthly_price_usd": 68.0,
          "included_ops": 50000,
          "overage_per_1000": 1.36
        },
        {
          "name": "Pro 100k",
          "monthly_price_usd": 129.0,
          "included_ops": 100000,
          "overage_per_1000": 1.29
        }
      ],
      "average_cost_per_task_usd": 0.0015,
      "notes": "Cost-effective visual workflow editor. 60% to 80% cheaper than Zapier for high-volume routing."
    },
    "n8n_cloud": {
      "name": "n8n (Managed Cloud)",
      "billing_model": "per_workflow_execution",
      "free_tier_ops": 0,
      "plans": [
        {
          "name": "Starter",
          "monthly_price_usd": 22.0,
          "included_executions": 2500,
          "overage_per_1000": 8.0
        },
        {
          "name": "Pro",
          "monthly_price_usd": 55.0,
          "included_executions": 10000,
          "overage_per_1000": 5.0
        },
        {
          "name": "Enterprise",
          "monthly_price_usd": 180.0,
          "included_executions": 50000,
          "overage_per_1000": 3.0
        }
      ],
      "notes": "Billed per entire workflow execution rather than individual step operations. Massive efficiency for complex trees."
    },
    "n8n_self_hosted_hostinger": {
      "name": "n8n Self-Hosted (Hostinger KVM2 VPS)",
      "billing_model": "fixed_infrastructure",
      "monthly_price_usd": 7.5,
      "monthly_price_eur": 6.99,
      "included_ops": 10000000,
      "vps_specs": "2 vCPU, 8 GB RAM, 100 GB NVMe, 8 TB Bandwidth, Docker Containerized",
      "notes": "100% Unlimited task execution. Total cost remains constant regardless of 10k or 1,000k tasks/month."
    },
    "n8n_self_hosted_digitalocean": {
      "name": "n8n Self-Hosted (DigitalOcean Basic Droplet)",
      "billing_model": "fixed_infrastructure",
      "monthly_price_usd": 12.0,
      "monthly_price_eur": 11.1,
      "included_ops": 10000000,
      "vps_specs": "2 vCPU, 2 GB RAM, 60 GB SSD, 3 TB Bandwidth, 1-Click Docker Marketplace",
      "notes": "Enterprise SLA uptime, 1-click Docker marketplace deploy, unlimited workflow executions."
    }
  },
  "vector_databases": {
    "supabase": {
      "name": "Supabase pgvector (PostgreSQL)",
      "free_tier_vectors": 50000,
      "pro_plan_monthly_usd": 25.0,
      "included_storage_gb": 8,
      "included_bandwidth_gb": 250,
      "overage_storage_per_gb_usd": 0.125,
      "read_query_cost_per_million_usd": 0.0,
      "notes": "Relational data + pgvector in one place. Predictable flat compute tiers without per-read microcharges."
    },
    "pinecone": {
      "name": "Pinecone Serverless",
      "free_tier_vectors": 100000,
      "base_fee_monthly_usd": 0.0,
      "read_unit_cost_per_million_usd": 0.25,
      "write_unit_cost_per_million_usd": 0.75,
      "storage_per_gb_monthly_usd": 0.33,
      "notes": "Pure serverless vector index. Pay-as-you-go per Read/Write unit, ideal for bursty sparse query traffic."
    },
    "qdrant_cloud": {
      "name": "Qdrant Cloud Managed",
      "free_tier_vectors": 100000,
      "cluster_base_monthly_usd": 25.0,
      "notes": "High performance Rust-based vector engine with payload filtering and hybrid search."
    }
  }
}