{
  "version": "5.1.1",
  "updated": "2026-08-23",
  "models": {
    "deepseek-flash": {
      "input": 0.0003,
      "output": 0.0012,
      "provider": "DeepSeek",
      "notes": "DeepSeek-V4.1-Flash, verified 2026-09-10. Peak cache-miss estimate; off-peak and cache-hit discounts excluded. See https://api-docs.deepseek.com/quick_start/pricing/"
    },
    "deepseek-v4-flash-vision-exp": {
      "input": 0.0003,
      "output": 0.0012,
      "provider": "DeepSeek",
      "notes": "Retired alias served by V4.1 Flash; peak cache-miss estimate."
    },
    "_comment_units": "All rates are USD per 1,000 tokens (per-1K). lib/costs.sh computes cost as (token_count / 1000) * rate, so every value here MUST be a per-1K rate = (provider $/1M price) / 1000. Do NOT paste $/MTok figures directly.",
    "_comment_premium": "Premium tier models - Sep 2026",
    "claude-fable-5-1": {
      "input": 0.01,
      "output": 0.05
    },
    "claude-opus-5": {
      "input": 0.005,
      "output": 0.025
    },
    "claude-fable-5": {
      "input": 0.01,
      "output": 0.05
    },
    "gemini-3.1-pro-preview": {
      "input": 0.00125,
      "output": 0.005
    },
    "_comment_agy": "Antigravity CLI (agy) addresses Gemini models by display name (v2.15). agy runs on OAuth/subscription auth; these per-1K rates mirror the matching Gemini API tier so the estimator stays consistent. gemini-3.1-pro-preview etc. above remain for GEMINI_USE_API mode.",
    "Gemini 3.1 Pro (High)": {
      "input": 0.002,
      "output": 0.012
    },
    "Gemini 3.6 Flash (High)": {
      "input": 0.0015,
      "output": 0.0075
    },
    "Gemini 3.6 Flash (Low)": {
      "input": 0.0015,
      "output": 0.0075
    },
    "gemini-3.7-flash": {
      "input": 0.00075,
      "output": 0.00375
    },
    "Gemini 3.7 Flash (High)": {
      "input": 0.00075,
      "output": 0.00375
    },
    "Gemini 3.7 Flash (Low)": {
      "input": 0.00075,
      "output": 0.00375
    },
    "gpt-6-astra": {
      "input": 0.01,
      "output": 0.05,
      "provider": "OpenAI",
      "notes": "Standard estimate; >272K input: 2x input, 1.5x output for full request. Cache/service adjustments excluded."
    },
    "gpt-5.6-sol": {
      "input": 0.004,
      "output": 0.020
    },
    "gpt-5.6-terra": {
      "input": 0.002,
      "output": 0.012
    },
    "gpt-5.6-luna": {
      "input": 0.0002,
      "output": 0.0012
    },
    "mistral-large-3": {
      "input": 0.002,
      "output": 0.006
    },
    "mistral-medium-3-5": {
      "input": 0.0015,
      "output": 0.0075
    },
    "mistral-medium-3.5": {
      "input": 0.0015,
      "output": 0.0075
    },
    "mistral-large-2512": {
      "input": 0.0005,
      "output": 0.0015
    },
    "mistral-small-2603": {
      "input": 0.00015,
      "output": 0.0006
    },
    "deepseek-v4-pro": {
      "input": 0.000435,
      "output": 0.00087
    },
    "glm-5.1": {
      "input": 0.0005,
      "output": 0.002
    },
    "grok-4.5": {
      "input": 0.002,
      "output": 0.006
    },
    "grok-4.6": {
      "input": 0.002,
      "output": 0.006
    },
    "qwen3.6-plus": {
      "input": 0.000325,
      "output": 0.00195
    },
    "qwen3.6-35b-a3b": {
      "input": 0.000163,
      "output": 0.0009
    },
    "composer-2": {
      "input": 0.0005,
      "output": 0.0025
    },
    "minimax-m2.7": {
      "input": 0.0003,
      "output": 0.0012
    },
    "minimax-m3": {
      "input": 0.0003,
      "output": 0.0012
    },
    "kimi-code/k3": {
      "input": 0.0005,
      "output": 0.002
    },
    "_comment_kimi_legacy": "Legacy Kimi alias retained only for historical and pinned-response cost lookup; v2.21.1 defaults to kimi-code/k3.",
    "kimi-code/kimi-for-coding": {
      "input": 0.0005,
      "output": 0.002
    },
    "nvidia/nemotron-3-super-120b-a12b:free": {
      "input": 0.00,
      "output": 0.00
    },
    "_comment_standard": "Standard tier models",
    "claude-sonnet-5": {
      "input": 0.003,
      "output": 0.015
    },
    "gemini-3-flash-preview": {
      "input": 0.000075,
      "output": 0.0003
    },
    "gpt-5.3": {
      "input": 0.0025,
      "output": 0.010
    },
    "mistral-medium-latest": {
      "input": 0.001,
      "output": 0.003
    },
    "deepseek-v3.2": {
      "input": 0.00027,
      "output": 0.0011
    },
    "grok-3": {
      "input": 0.003,
      "output": 0.009
    },
    "_comment_economy": "Economy tier models",
    "claude-haiku-4-5": {
      "input": 0.001,
      "output": 0.005
    },
    "gemini-2.0-flash": {
      "input": 0.0001,
      "output": 0.0004
    },
    "gpt-4o-mini": {
      "input": 0.00015,
      "output": 0.0006
    },
    "devstral-small-2": {
      "input": 0,
      "output": 0
    },
    "deepseek-chat": {
      "input": 0.001,
      "output": 0.002
    },
    "glm-4-flash": {
      "input": 0.001,
      "output": 0.003
    },
    "grok-3-mini": {
      "input": 0.001,
      "output": 0.003
    },
    "qwen3-32b": {
      "input": 0.0004,
      "output": 0.0016
    },
    "minimax-m2.5": {
      "input": 0.0003,
      "output": 0.0012
    },
    "_comment_legacy": "Legacy models for backwards compatibility",
    "Gemini 3.5 Flash (High)": {
      "input": 0.0015,
      "output": 0.009
    },
    "Gemini 3.5 Flash (Low)": {
      "input": 0.0015,
      "output": 0.009
    },
    "gpt-5.5": {
      "input": 0.005,
      "output": 0.030
    },
    "gpt-5.4": {
      "input": 0.0025,
      "output": 0.015
    },
    "gpt-5.4-nano": {
      "input": 0.0002,
      "output": 0.00125
    },
    "claude-sonnet-4-6": {
      "input": 0.003,
      "output": 0.015
    },
    "claude-opus-4-8": {
      "input": 0.005,
      "output": 0.025
    },
    "claude-opus-4-7": {
      "input": 0.005,
      "output": 0.025
    },
    "opus-4.6": {
      "input": 0.005,
      "output": 0.025
    },
    "sonnet-4.6": {
      "input": 0.003,
      "output": 0.015
    },
    "haiku-4.5": {
      "input": 0.001,
      "output": 0.005
    },
    "gpt-5.3-codex": {
      "input": 0.003,
      "output": 0.012
    },
    "composer-1.5": {
      "input": 0.005,
      "output": 0.015
    },
    "deepseek-reasoner": {
      "input": 0.00055,
      "output": 0.00219
    },
    "qwen3.5-plus": {
      "input": 0.0016,
      "output": 0.0064
    },
    "grok-4.20-0309-reasoning": {
      "input": 0.005,
      "output": 0.015
    },
    "claude-opus-4-5-20251124": {
      "input": 0.005,
      "output": 0.025
    },
    "claude-sonnet-4-5-20251124": {
      "input": 0.003,
      "output": 0.015
    },
    "claude-3-5-haiku-20241022": {
      "input": 0.0008,
      "output": 0.004
    },
    "gpt-5.2-codex": {
      "input": 0.003,
      "output": 0.012
    },
    "gpt-5.2": {
      "input": 0.0025,
      "output": 0.010
    },
    "gpt-4": {
      "input": 0.03,
      "output": 0.06
    },
    "gpt-4-turbo": {
      "input": 0.01,
      "output": 0.03
    },
    "gpt-4o": {
      "input": 0.005,
      "output": 0.015
    },
    "o1": {
      "input": 0.015,
      "output": 0.06
    },
    "o3": {
      "input": 0.015,
      "output": 0.06
    },
    "claude-3-opus": {
      "input": 0.015,
      "output": 0.075
    },
    "claude-3-sonnet": {
      "input": 0.003,
      "output": 0.015
    },
    "claude-3-haiku": {
      "input": 0.00025,
      "output": 0.00125
    },
    "mistral-large": {
      "input": 0.004,
      "output": 0.012
    },
    "mistral-medium": {
      "input": 0.0027,
      "output": 0.0081
    },
    "mistral-small": {
      "input": 0.001,
      "output": 0.003
    },
    "glm-4.7": {
      "input": 0.0005,
      "output": 0.002
    },
    "qwen3-max": {
      "input": 0.0016,
      "output": 0.0064
    },
    "qwen3-235b-a22b": {
      "input": 0.0008,
      "output": 0.0032
    },
    "cursor": {
      "input": 0.005,
      "output": 0.015
    },
    "qwen-max": {
      "input": 0.004,
      "output": 0.012
    },
    "qwen-plus": {
      "input": 0.002,
      "output": 0.006
    },
    "qwen-turbo": {
      "input": 0.0008,
      "output": 0.002
    },
    "glm-4": {
      "input": 0.003,
      "output": 0.009
    },
    "glm-3-turbo": {
      "input": 0.001,
      "output": 0.003
    },
    "grok-2": {
      "input": 0.01,
      "output": 0.03
    },
    "deepseek-coder": {
      "input": 0.001,
      "output": 0.002
    },
    "minimax-m2.1": {
      "input": 0.0003,
      "output": 0.0015
    },
    "composer-2.5": {
      "input": 0.0005,
      "output": 0.0025
    },
    "gemini-3-flash": {
      "input": 0.0005,
      "output": 0.003
    },
    "deepseek-v4-flash": {
      "input": 0.0003,
      "output": 0.0012
    },
    "glm-5.2": {
      "input": 0.00098,
      "output": 0.00308
    },
    "grok-4.1-fast": {
      "input": 0.0002,
      "output": 0.0005
    },
    "qwen3.7-max": {
      "input": 0.0012,
      "output": 0.006
    },
    "grok-4.3": {
      "input": 0.00125,
      "output": 0.0025
    },
    "_comment_unpriced": "Credit-billed models: drawn from a prepaid subscription pool, with no published per-token price. Rated 0 so the estimator does not fabricate a figure - an absent model would otherwise fall through to default_rate (0.005/0.015) and be reported as a confident, wrong number. Every entry here must also be listed in unpriced_models, which is what makes the session report disclose the exclusion instead of implying the model was free.",
    "qwen3.8-max": {
      "input": 0,
      "output": 0
    },
    "qwen3.8-max-preview": {
      "input": 0,
      "output": 0
    },
    "glm-5.3": {
      "input": 0,
      "output": 0
    },
    "glm-5.3-flash": {
      "input": 0,
      "output": 0
    },
    "kimi-code/k3-256k": {
      "input": 0,
      "output": 0
    }
  },
  "unpriced_models": [
    "qwen3.8-max",
    "qwen3.8-max-preview",
    "glm-5.3",
    "glm-5.3-flash",
    "kimi-code/k3-256k"
  ],
  "consultant_fallbacks": {
    "_comment": "Premium defaults - Updated Sep 2026",
    "claude": "claude-fable-5-1",
    "gemini": "Gemini 3.7 Flash (High)",
    "codex": "gpt-6-astra",
    "mistral": "mistral-large-3",
    "deepseek": "deepseek-flash",
    "glm": "glm-5.3-flash",
    "grok": "grok-4.6",
    "qwen3": "qwen3.7-max",
    "kimi": "kimi-code/k3",
    "minimax": "minimax-m2.7"
  },
  "model_tiers": {
    "_comment": "Model tiers for apply_model_tier() function",
    "maximum": {
      "claude": "claude-fable-5-1",
      "gemini": "Gemini 3.7 Flash (High)",
      "codex": "gpt-6-astra",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.6",
      "qwen3": "qwen3.8-max",
      "kimi": "kimi-code/k3-256k",
      "minimax": "MiniMax-M3"
    },
    "premium": {
      "claude": "claude-fable-5-1",
      "gemini": "Gemini 3.7 Flash (High)",
      "codex": "gpt-6-astra",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.6",
      "qwen3": "qwen3.7-max",
      "kimi": "kimi-code/k3",
      "minimax": "MiniMax-M2.7"
    },
    "standard": {
      "claude": "claude-opus-5",
      "gemini": "Gemini 3.7 Flash (High)",
      "codex": "gpt-5.6-terra",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.5",
      "qwen3": "qwen3.6-35b-a3b",
      "kimi": "kimi-code/k3",
      "minimax": "MiniMax-M2.7"
    },
    "economy": {
      "claude": "claude-haiku-4-5",
      "gemini": "Gemini 3.7 Flash (Low)",
      "codex": "gpt-5.6-luna",
      "mistral": "devstral-small-2",
      "deepseek": "deepseek-flash",
      "glm": "glm-4-flash",
      "grok": "grok-4.5",
      "qwen3": "qwen3-32b",
      "kimi": "kimi-code/k3",
      "minimax": "MiniMax-M2.5"
    }
  },
  "transport_model_tiers": {
    "_comment": "Transport-specific namespaces used by Gemini and Mistral; the legacy model_tiers table reflects their CLI values.",
    "gemini": {
      "maximum": {"cli": "Gemini 3.7 Flash (High)", "api": "gemini-3.1-pro-preview"},
      "premium": {"cli": "Gemini 3.7 Flash (High)", "api": "gemini-3.1-pro-preview"},
      "standard": {"cli": "Gemini 3.7 Flash (High)", "api": "gemini-3.1-pro-preview"},
      "economy": {"cli": "Gemini 3.7 Flash (Low)", "api": "gemini-3.1-pro-preview"}
    },
    "mistral": {
      "maximum": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
      "premium": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
      "standard": {"cli": "mistral-medium-3.5", "api": "mistral-large-3"},
      "economy": {"cli": "devstral-small-2", "api": "mistral-large-3"}
    }
  },
  "opt_in_targets": {
    "gemini_cli": ["Gemini 3.1 Pro (High)", "Gemini 3.6 Flash (High)", "Gemini 3.6 Flash (Low)"],
    "gemini_api": ["gemini-3.7-flash"],
    "mistral_api": ["mistral-medium-3-5", "mistral-large-2512", "mistral-small-2603"],
    "claude": []
  },
  "default_rate": {
    "input": 0.005,
    "output": 0.015
  }
}