{
  "schema_version": "1.0",
  "name": "SXF AI Model Pricing & Specs Database",
  "description": "Canonical Standard API pricing and core specifications for selected frontier AI models tracked by SXF / AI.",
  "source_verified": "2026-09-27",
  "currency": "USD",
  "pricing_unit": "per 1 million tokens",
  "pricing_scope": "Standard API token pricing unless a model-specific rule states otherwise",
  "calculator_excludes": [
    "Batch, Flex, Fast, Priority, or other non-Standard service tiers",
    "Prompt-cache write and cache-storage charges",
    "Tool, grounding, search, code execution, and other add-on charges",
    "Regional or data-residency uplifts",
    "Enterprise, volume, committed-use, or negotiated discounts"
  ],
  "models": [
    {
      "provider": "OpenAI",
      "family": "GPT-6",
      "model": "GPT-6 Astra",
      "model_id": "gpt-6-astra",
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-04-30",
      "reasoning": {"type": "reasoning effort", "levels": ["low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Highest-capability GPT-6 tier for demanding reasoning, coding, computer use, research, and document creation.",
      "sxf_url": "/models/gpt-6-astra/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-6-astra", "https://developers.openai.com/api/docs/pricing"],
      "pricing": {
        "standard": [{"start": "2026-09-03", "end": null, "input": 10.0, "cached_input": 1.0, "cache_write": 12.5, "output": 50.0}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "OpenAI",
      "family": "GPT-6",
      "model": "GPT-6 Sol",
      "model_id": "gpt-6-sol",
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-04-20",
      "reasoning": {"type": "reasoning effort", "levels": ["none", "low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "General-purpose GPT-6 tier for complex coding and agentic workflows with lower unit cost than Astra.",
      "sxf_url": "/models/gpt-6-sol/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-6-sol", "https://developers.openai.com/api/docs/pricing"],
      "pricing": {
        "standard": [{"start": "2026-09-22", "end": null, "input": 2.0, "cached_input": 0.2, "cache_write": 2.5, "output": 10.0}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "OpenAI",
      "family": "GPT-6",
      "model": "GPT-6 Luna",
      "model_id": "gpt-6-luna",
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-05-18",
      "reasoning": {"type": "reasoning effort", "levels": ["none", "low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Efficiency-focused GPT-6 tier for focused, high-volume, and cost-sensitive workloads.",
      "sxf_url": "/models/gpt-6-luna/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-6-luna", "https://developers.openai.com/api/docs/pricing"],
      "pricing": {
        "standard": [{"start": "2026-09-22", "end": null, "input": 0.1, "cached_input": 0.01, "cache_write": 0.125, "output": 0.5}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "OpenAI",
      "family": "GPT-5.6",
      "model": "GPT-5.6 Sol",
      "model_id": "gpt-5.6-sol",
      "aliases": ["gpt-5.6"],
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-02-16",
      "reasoning": {"type": "reasoning effort", "levels": ["none", "low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Flagship GPT-5.6 tier for complex professional work, coding, research, and agentic workflows.",
      "sxf_url": "/models/gpt-5-6-sol/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-5.6-sol", "https://developers.openai.com/api/docs/pricing"],
      "notes": ["Current $4/$20 Standard rates are promotional through at least November 21, 2026."],
      "pricing": {
        "standard": [{"start": "2026-07-09", "end": null, "input": 4.0, "cached_input": 0.4, "cache_write": 5.0, "output": 20.0}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "OpenAI",
      "family": "GPT-5.6",
      "model": "GPT-5.6 Terra",
      "model_id": "gpt-5.6-terra",
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-02-16",
      "reasoning": {"type": "reasoning effort", "levels": ["none", "low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "GPT-5.6 tier balancing intelligence and cost for production workloads.",
      "sxf_url": "/models/gpt-5-6/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-5.6-terra", "https://developers.openai.com/api/docs/pricing"],
      "pricing": {
        "standard": [{"start": "2026-07-30", "end": null, "input": 2.0, "cached_input": 0.2, "cache_write": 2.5, "output": 12.0}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "OpenAI",
      "family": "GPT-5.6",
      "model": "GPT-5.6 Luna",
      "model_id": "gpt-5.6-luna",
      "context_window": 1050000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-02-16",
      "reasoning": {"type": "reasoning effort", "levels": ["none", "low", "medium", "high", "xhigh", "max"], "default": "medium"},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Lowest-cost GPT-5.6 tier for cost-sensitive, high-volume workloads.",
      "sxf_url": "/models/gpt-5-6-luna/",
      "official_sources": ["https://developers.openai.com/api/docs/models/gpt-5.6-luna", "https://developers.openai.com/api/docs/pricing"],
      "pricing": {
        "standard": [{"start": "2026-07-30", "end": null, "input": 0.2, "cached_input": 0.02, "cache_write": 0.25, "output": 1.2}],
        "long_context": {"threshold_input_tokens": 272000, "condition": "total input tokens greater than 272000", "applies_to_entire_request": true, "multipliers": {"input": 2.0, "cached_input": 2.0, "cache_write": 2.0, "output": 1.5}}
      }
    },
    {
      "provider": "Anthropic",
      "family": "Claude 5",
      "model": "Claude Fable 5.1",
      "model_id": "claude-fable-5-1",
      "context_window": 1000000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-06",
      "reasoning": {"type": "adaptive thinking", "levels": ["effort controlled"], "default": "high", "always_on": true},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Anthropic's highest-capability generally available model for demanding reasoning and long-horizon agentic work.",
      "sxf_url": "/models/claude-fable-5-1/",
      "official_sources": ["https://platform.claude.com/docs/en/models/fable-5-1/overview", "https://platform.claude.com/docs/en/about-claude/pricing"],
      "pricing": {"standard": [{"start": "2026-09-01", "end": null, "input": 10.0, "cached_input": 0.25, "cache_write_5m": 12.5, "cache_write_1h": 20.0, "output": 50.0}]}
    },
    {
      "provider": "Anthropic",
      "family": "Claude 5",
      "model": "Claude Opus 5.5",
      "model_id": "claude-opus-5-5",
      "context_window": 1000000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-06",
      "reasoning": {"type": "adaptive thinking", "levels": ["effort controlled"], "default": "medium", "always_on": true},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Current Opus model for long-running agentic coding and complex knowledge work.",
      "sxf_url": "/models/claude-opus-5-5/",
      "official_sources": ["https://platform.claude.com/docs/en/models/opus-5-5/overview", "https://platform.claude.com/docs/en/about-claude/pricing"],
      "pricing": {"standard": [{"start": "2026-09-22", "end": null, "input": 4.0, "cached_input": 0.2, "cache_write_5m": 5.0, "cache_write_1h": 8.0, "output": 20.0}]}
    },
    {
      "provider": "Anthropic",
      "family": "Claude 5",
      "model": "Claude Sonnet 5",
      "model_id": "claude-sonnet-5",
      "context_window": 1000000,
      "max_output": 128000,
      "knowledge_cutoff": "2026-01",
      "reasoning": {"type": "adaptive thinking", "levels": ["effort controlled"], "default": "high", "always_on": false},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Balanced Claude tier combining speed and intelligence for coding, agents, and production knowledge work.",
      "sxf_url": "/guides/gpt-6-vs-claude/",
      "official_sources": ["https://platform.claude.com/docs/en/models/sonnet-5/overview", "https://platform.claude.com/docs/en/about-claude/pricing"],
      "pricing": {"standard": [{"start": "2026-06-30", "end": null, "input": 2.0, "cached_input": 0.2, "cache_write_5m": 2.5, "cache_write_1h": 4.0, "output": 10.0}]}
    },
    {
      "provider": "Anthropic",
      "family": "Claude 4",
      "model": "Claude Haiku 4.5",
      "model_id": "claude-haiku-4-5-20251001",
      "aliases": ["claude-haiku-4-5"],
      "context_window": 200000,
      "max_output": 64000,
      "knowledge_cutoff": "2025-02",
      "reasoning": {"type": "extended thinking", "levels": ["manual budget"], "default": null, "always_on": false},
      "modalities": {"input": ["text", "image"], "output": ["text"]},
      "positioning": "Fastest Claude tier for latency-sensitive and high-volume workloads.",
      "sxf_url": "/guides/gpt-6-vs-claude/",
      "official_sources": ["https://platform.claude.com/docs/en/models/haiku-4-5/overview", "https://platform.claude.com/docs/en/about-claude/pricing"],
      "pricing": {"standard": [{"start": "2025-10-15", "end": null, "input": 1.0, "cached_input": 0.1, "cache_write_5m": 1.25, "cache_write_1h": 2.0, "output": 5.0}]}
    },
    {
      "provider": "Google",
      "family": "Gemini 3",
      "model": "Gemini 3.8 Flash",
      "model_id": "gemini-3.8-flash",
      "context_window": 1048576,
      "max_output": 65536,
      "knowledge_cutoff": null,
      "reasoning": {"type": "thinking level", "levels": ["low", "medium", "high"], "default": "medium"},
      "modalities": {"input": ["text", "image", "video", "audio", "PDF"], "output": ["text"]},
      "positioning": "Google's most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.",
      "sxf_url": "/models/gemini-3-8-flash/",
      "official_sources": ["https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash", "https://ai.google.dev/gemini-api/docs/pricing"],
      "notes": ["Introductory Standard pricing applies through December 31, 2026; higher Standard pricing starts January 1, 2027."],
      "pricing": {
        "standard": [
          {"start": "2026-09-02", "end": "2026-12-31", "input": 0.75, "cached_input": 0.075, "output": 3.75},
          {"start": "2027-01-01", "end": null, "input": 1.5, "cached_input": 0.15, "output": 7.5}
        ]
      }
    }
  ]
}