{
  "$schema_version": 1,
  "_comment": "Rolling pricing table consumed by loki-ts/src/runner/budget.ts and, for the .loki/pricing.json rows, by autonomy/run.sh _write_pricing_json (optional per-row label; provider is codex for gpt-* keys, else claude). Update this file when Anthropic / OpenAI / others publish new prices; no code change required. Pricing is USD per 1 million tokens. Aliases (opus/sonnet/haiku) point to the latest model of that family per providers/model_catalog.json.",
  "_updated": "2026-10-08",
  "default_max_cost_usd": 100,
  "inference_geo_multipliers": {"us": 1.1},
  "_source": "https://platform.claude.com/docs/en/about-claude/pricing (docs.anthropic.com/en/docs/about-claude/pricing 301-redirects there), read 2026-10-08. Per MTok. fable=Claude Fable 5.1 $10/$50, cache read $0.25 (0.025x), 5m write $12.50, 1h write $20. opus=Claude Opus 5.5 $4/$20, cache read $0.20 (0.05x), 5m write $5, 1h write $8. sonnet=Claude Sonnet 5.5 $2/$10, cache read $0.10 (0.05x), 5m write $2.50, 1h write $4. haiku alias row prices as its catalog target claude-haiku-5-5 (providers/model_catalog.json cli_aliases), so it equals that row including over_100k; Haiku 4.5 ($1/$5) is no longer an alias target. claude-haiku-5-5 (exact id, same as the haiku alias): $0.10/$0.50, read $0.01, 5m $0.125, 1h $0.20 up to 100,000 prompt tokens; over_100k $0.50/$2.50, read $0.05, 5m $0.625, 1h $1. Fields: cache_write is the 5m write rate (legacy readers); cache_write_5m and cache_write_1h are the explicit tiers. Multipliers: 5m write 1.25x, 1h write 2x, read 0.1x (0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1). OpenAI rows (gpt-5.3-codex, gpt-5.6-sol/terra/luna): https://developers.openai.com/api/docs/pricing, read 2026-10-08, Standard tier, short context (up to 272K); cached input is the cache_read field; OpenAI bills no cache write, cache_write is a 1.25x placeholder.",
  "pricing": {
    "fable": {
      "label": "Fable 5 (top tier)",
      "input": 10.0,
      "output": 50.0,
      "cache_read": 0.25,
      "cache_write": 12.5,
      "cache_write_5m": 12.5,
      "cache_write_1h": 20.0
    },
    "claude-fable-5": {
      "label": "Fable 5 (top tier)",
      "input": 10.0,
      "output": 50.0,
      "cache_read": 0.25,
      "cache_write": 12.5,
      "cache_write_5m": 12.5,
      "cache_write_1h": 20.0
    },
    "opus": {
      "label": "Opus (latest)",
      "input": 4.0,
      "output": 20.0,
      "cache_read": 0.2,
      "cache_write": 5,
      "cache_write_5m": 5,
      "cache_write_1h": 8.0
    },
    "sonnet": {
      "label": "Sonnet (latest)",
      "input": 2.0,
      "output": 10.0,
      "cache_read": 0.1,
      "cache_write": 2.5,
      "cache_write_5m": 2.5,
      "cache_write_1h": 4.0
    },
    "haiku": {
      "label": "Haiku 5.5 (latest)",
      "input": 0.1,
      "output": 0.5,
      "cache_read": 0.01,
      "cache_write": 0.125,
      "over_100k": {
        "input": 0.5,
        "output": 2.5,
        "cache_read": 0.05,
        "cache_write": 0.625,
        "cache_write_5m": 0.625,
        "cache_write_1h": 1.0
      },
      "cache_write_5m": 0.125,
      "cache_write_1h": 0.2
    },
    "claude-haiku-4-5": {
      "label": "Haiku 4.5",
      "input": 1.0,
      "output": 5.0,
      "cache_read": 0.1,
      "cache_write": 1.25,
      "cache_write_5m": 1.25,
      "cache_write_1h": 2.0
    },
    "claude-haiku-5-5": {
      "label": "Haiku 5.5",
      "input": 0.1,
      "output": 0.5,
      "cache_read": 0.01,
      "cache_write": 0.125,
      "over_100k": {
        "input": 0.5,
        "output": 2.5,
        "cache_read": 0.05,
        "cache_write": 0.625,
        "cache_write_5m": 0.625,
        "cache_write_1h": 1.0
      },
      "cache_write_5m": 0.125,
      "cache_write_1h": 0.2
    },
    "gpt-5.3-codex": {
      "label": "GPT-5.3 Codex",
      "input": 1.75,
      "output": 14.0,
      "cache_read": 0.175,
      "cache_write": 2.1875
    },
    "gpt-5.6-sol": {
      "label": "GPT-5.6 Sol",
      "input": 4.0,
      "output": 20.0,
      "cache_read": 0.4,
      "cache_write": 5.0
    },
    "gpt-5.6-terra": {
      "label": "GPT-5.6 Terra",
      "input": 2.0,
      "output": 12.0,
      "cache_read": 0.2,
      "cache_write": 2.5
    },
    "gpt-5.6-luna": {
      "label": "GPT-5.6 Luna",
      "input": 0.2,
      "output": 1.2,
      "cache_read": 0.02,
      "cache_write": 0.25
    }
  }
}