{
  "version": "5.8.0",
  "updated": "2026-10-28",
  "models": {
    "_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_scope": "Current models only (5.5.0). Superseded models are listed in retired_models with their replacement; configure migrates them and the runtime warns. A model absent from this table is reported as unpriced, never priced at a guessed rate. Rates are official list prices, Verified 2026-10-24.",
    "_comment_agy": "Antigravity CLI (agy) addresses Gemini models by display name and runs on subscription auth; these rates mirror the matching Gemini API model so the estimator stays consistent.",
    "_comment_unpriced": "Subscription-billed transports: these consultants run on a plan that bills by quota (Kimi Code, Qwen Token Plan, GLM coding-plan endpoint), not per token. Rated 0 and listed in unpriced_models, so the session report discloses the exclusion instead of implying the model was free. For reference, the pay-as-you-go API prices per 1M are: kimi-k3.1-pro $2/$10, qwen3.8-max $2/$6, qwen3.8-flash $0.15/$0.47, GLM-5.3 $1.40/$4.40, GLM-5.3-Flash $0.15/$0.50 (Verified 2026-10-24.)",
    "claude-fable-5-1": {
      "input": 0.01,
      "output": 0.05,
      "provider": "Anthropic",
      "notes": "Standard API list rate ($10/$50 per 1M). Cache and batch adjustments excluded. Verified 2026-10-25 (https://platform.claude.com/docs/en/about-claude/pricing)."
    },
    "claude-opus-5-5": {
      "input": 0.004,
      "output": 0.02,
      "provider": "Anthropic",
      "notes": "Standard API list rate ($4/$20 per 1M). Cache and batch adjustments excluded. Verified 2026-10-25 (https://platform.claude.com/docs/en/about-claude/pricing)."
    },
    "claude-sonnet-5-5": {
      "input": 0.002,
      "output": 0.01,
      "provider": "Anthropic",
      "notes": "Standard API list rate ($2/$10 per 1M). Cache and batch adjustments excluded. Verified 2026-10-25 (https://platform.claude.com/docs/en/about-claude/pricing)."
    },
    "claude-haiku-5-5": {
      "input": 0.0001,
      "output": 0.0005,
      "provider": "Anthropic",
      "notes": "Standard API list rate ($0.10/$0.50 per 1M). Cache and batch adjustments excluded. Above 100K input tokens: $0.50/$2.50 (the whole request bills at this rate). Verified 2026-10-25 (https://platform.claude.com/docs/en/about-claude/pricing)."
    },
    "gemini-4-argon": {
      "input": 0.004,
      "output": 0.02,
      "provider": "Google",
      "notes": "Standard API list rate ($4/$20 per 1M). List rate from 2026-12-01; introductory 2/10 through 2026-11-30. Verified 2026-10-25 (https://ai.google.dev/gemini-api/docs/pricing)."
    },
    "gemini-4-argon-low": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for gemini-4-argon-low (gemini-4-argon); not a CLI invoice."
    },
    "gemini-4-argon-medium": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for gemini-4-argon-medium (gemini-4-argon); not a CLI invoice."
    },
    "gemini-4-argon-high": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for gemini-4-argon-high (gemini-4-argon); not a CLI invoice."
    },
    "Gemini 4 Argon (Low)": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for Gemini 4 Argon (Low) (gemini-4-argon); not a CLI invoice."
    },
    "Gemini 4 Argon (Medium)": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for Gemini 4 Argon (Medium) (gemini-4-argon); not a CLI invoice."
    },
    "Gemini 4 Argon (High)": {
      "input": 0.004,
      "output": 0.02,
      "notes": "API-equivalent estimate for Gemini 4 Argon (High) (gemini-4-argon); not a CLI invoice."
    },
    "gemini-3.8-flash": {
      "input": 0.00075,
      "output": 0.00375,
      "provider": "Google",
      "notes": "Promotional rate ($0.75/$3.75 per 1M). Standard rate from 2027-01-01; promotional 0.75/3.75 through 2026-12-31. Verified 2026-10-25 (https://ai.google.dev/gemini-api/docs/pricing)."
    },
    "gemini-3.8-flash-low": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for gemini-3.8-flash-low (gemini-3.8-flash); not a CLI invoice."
    },
    "gemini-3.8-flash-medium": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for gemini-3.8-flash-medium (gemini-3.8-flash); not a CLI invoice."
    },
    "gemini-3.8-flash-high": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for gemini-3.8-flash-high (gemini-3.8-flash); not a CLI invoice."
    },
    "Gemini 3.8 Flash (Low)": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for Gemini 3.8 Flash (Low) (gemini-3.8-flash); not a CLI invoice."
    },
    "Gemini 3.8 Flash (Medium)": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for Gemini 3.8 Flash (Medium) (gemini-3.8-flash); not a CLI invoice."
    },
    "Gemini 3.8 Flash (High)": {
      "input": 0.00075,
      "output": 0.00375,
      "notes": "API-equivalent estimate for Gemini 3.8 Flash (High) (gemini-3.8-flash); not a CLI invoice."
    },
    "gpt-6-astra": {
      "input": 0.01,
      "output": 0.05,
      "provider": "OpenAI",
      "notes": "Standard API list rate ($10/$50 per 1M). Above 272K input tokens the long-context rates apply. Verified 2026-10-25 (https://developers.openai.com/api/docs/pricing)."
    },
    "gpt-6.1-sol": {
      "input": 0.002,
      "output": 0.01,
      "provider": "OpenAI",
      "notes": "Standard API list rate ($2/$10 per 1M). Above 272K input tokens the long-context rates apply. Verified 2026-10-25 (https://developers.openai.com/api/docs/pricing)."
    },
    "gpt-6.1-terra": {
      "input": 0.001,
      "output": 0.005,
      "provider": "OpenAI",
      "notes": "Standard API list rate ($1/$5 per 1M). Standard USD per 1M tokens. Cached input $0.05. Above 272K input tokens, the long-context rates apply to the full request. Above 272K input tokens: $2/$7.50. Verified 2026-10-27 (https://developers.openai.com/api/docs/pricing)."
    },
    "gpt-6-luna": {
      "input": 0.0001,
      "output": 0.0005,
      "provider": "OpenAI",
      "notes": "Standard API list rate ($0.10/$0.50 per 1M). Verified 2026-10-25 (https://developers.openai.com/api/docs/pricing)."
    },
    "mistral-large-4": {
      "input": 0.00136,
      "output": 0.00418,
      "provider": "Mistral",
      "notes": "Standard API list rate ($1.36/$4.18 per 1M). Verified 2026-10-25 (https://docs.mistral.ai/models/mistral-large-4-0)."
    },
    "mistral-large-4-0": {
      "input": 0.00136,
      "output": 0.00418
    },
    "mistral-medium-3.5": {
      "input": 0.0015,
      "output": 0.0075,
      "provider": "Mistral",
      "notes": "Standard API list rate ($1.50/$7.50 per 1M). Verified 2026-10-25 (https://docs.mistral.ai/models/mistral-medium-3-5-26-04)."
    },
    "mistral-medium-3-5": {
      "input": 0.0015,
      "output": 0.0075
    },
    "mistral-small-2603": {
      "input": 0.00015,
      "output": 0.0006,
      "provider": "Mistral",
      "notes": "Standard API list rate ($0.15/$0.60 per 1M). Verified 2026-10-25 (https://docs.mistral.ai/models/mistral-small-4-0-26-03)."
    },
    "deepseek-flash": {
      "input": 0.0003,
      "output": 0.0012,
      "provider": "DeepSeek",
      "notes": "Standard API list rate ($0.30/$1.20 per 1M). Peak cache-miss rate; off-peak 0.15/0.60. Verified 2026-10-25 (https://api-docs.deepseek.com/quick_start/pricing)."
    },
    "deepseek-v4-pro": {
      "input": 0.00132,
      "output": 0.00396,
      "provider": "DeepSeek",
      "notes": "Standard API list rate ($1.32/$3.96 per 1M). Peak rate. Verified 2026-10-25 (https://api-docs.deepseek.com/quick_start/pricing)."
    },
    "grok-4.7": {
      "input": 0.002,
      "output": 0.006,
      "provider": "xAI",
      "notes": "Standard API list rate ($2/$6 per 1M). At or above 200K input tokens: 4/12. Above 200K input tokens: $4/$12. Verified 2026-10-25 (https://docs.x.ai/docs/models)."
    },
    "minimax-m3.1-flash": {
      "input": 0.00015,
      "output": 0.0006,
      "provider": "MiniMax",
      "notes": "Standard API list rate ($0.15/$0.60 per 1M). Verified 2026-10-25 (https://platform.minimax.io/docs/guides/pricing)."
    },
    "muse-wonder-1.0": {
      "input": 0.004,
      "output": 0.02,
      "provider": "Meta",
      "notes": "Standard API list rate ($4/$20 per 1M). Cached input 0.20. Verified 2026-10-25 (https://dev.meta.ai/docs/pricing-rate-limits)."
    },
    "muse-spark-1.3": {
      "input": 0.00125,
      "output": 0.00425,
      "provider": "Meta",
      "notes": "Standard API list rate ($1.25/$4.25 per 1M). Cached input 0.15. Verified 2026-10-25 (https://dev.meta.ai/docs/pricing-rate-limits)."
    },
    "muse-spark-1.3-contributor": {
      "input": 0.0001,
      "output": 0.0002,
      "provider": "Meta",
      "notes": "Standard API list rate ($0.10/$0.20 per 1M). Content is used for training (Contributor mode). Verified 2026-10-25 (https://dev.meta.ai/docs/pricing-rate-limits)."
    },
    "kimi-code/k3.1-pro": {
      "input": 0,
      "output": 0
    },
    "qwen3.8-max": {
      "input": 0,
      "output": 0
    },
    "qwen3.8-flash": {
      "input": 0,
      "output": 0
    },
    "glm-5.3": {
      "input": 0,
      "output": 0
    },
    "glm-5.3-flash": {
      "input": 0,
      "output": 0
    }
  },
  "unpriced_models": [
    "kimi-code/k3.1-pro",
    "qwen3.8-max",
    "qwen3.8-flash",
    "glm-5.3",
    "glm-5.3-flash"
  ],
  "retired_models": {
    "_comment": "Superseded models (removed in 5.5.0) -> current replacement. configure migrates a persisted value, pinned or not, and records migrated-from; the runtime warns when one is still selected. null: the consultant itself was removed.",
    "claude-fable-5": "claude-fable-5-1",
    "claude-opus-5": "claude-opus-5-5",
    "claude-opus-4-8": "claude-opus-5-5",
    "claude-opus-4-7": "claude-opus-5-5",
    "opus-4.6": "claude-opus-5-5",
    "claude-opus-4-5-20251124": "claude-opus-5-5",
    "claude-3-opus": "claude-opus-5-5",
    "claude-sonnet-5": "claude-sonnet-5-5",
    "claude-sonnet-4-6": "claude-sonnet-5-5",
    "sonnet-4.6": "claude-sonnet-5-5",
    "claude-sonnet-4-5-20251124": "claude-sonnet-5-5",
    "claude-3-sonnet": "claude-sonnet-5-5",
    "claude-haiku-4-5": "claude-haiku-5-5",
    "haiku-4.5": "claude-haiku-5-5",
    "claude-3-5-haiku-20241022": "claude-haiku-5-5",
    "claude-3-haiku": "claude-haiku-5-5",
    "Gemini 3.1 Pro (High)": "gemini-4-argon-high",
    "Gemini 3.7 Flash (High)": "gemini-3.8-flash-high",
    "Gemini 3.6 Flash (High)": "gemini-3.8-flash-high",
    "Gemini 3.5 Flash (High)": "gemini-3.8-flash-high",
    "Gemini 3.7 Flash (Low)": "gemini-3.8-flash-low",
    "Gemini 3.6 Flash (Low)": "gemini-3.8-flash-low",
    "Gemini 3.5 Flash (Low)": "gemini-3.8-flash-low",
    "gemini-3.1-pro-preview": "gemini-4-argon",
    "gemini-3.7-flash": "gemini-3.8-flash",
    "gemini-3-flash": "gemini-3.8-flash",
    "gemini-3-flash-preview": "gemini-3.8-flash",
    "gemini-2.0-flash": "gemini-3.8-flash",
    "gpt-5.6-sol": "gpt-6.1-sol",
    "gpt-5.6-terra": "gpt-6.1-terra",
    "gpt-5.5": "gpt-6.1-sol",
    "gpt-5.4": "gpt-6.1-sol",
    "gpt-5.3": "gpt-6.1-sol",
    "gpt-5.3-codex": "gpt-6.1-sol",
    "gpt-5.2": "gpt-6.1-sol",
    "gpt-5.2-codex": "gpt-6.1-sol",
    "gpt-4": "gpt-6.1-sol",
    "gpt-4-turbo": "gpt-6.1-sol",
    "gpt-4o": "gpt-6.1-sol",
    "o1": "gpt-6.1-sol",
    "o3": "gpt-6.1-sol",
    "gpt-5.6-luna": "gpt-6-luna",
    "gpt-5.4-nano": "gpt-6-luna",
    "gpt-4o-mini": "gpt-6-luna",
    "mistral-large-3": "mistral-large-4",
    "mistral-large-2512": "mistral-large-4",
    "mistral-large": "mistral-large-4",
    "mistral-medium-latest": "mistral-large-4",
    "mistral-medium": "mistral-large-4",
    "mistral-small": "mistral-small-2603",
    "devstral-small-2": "mistral-medium-3.5",
    "deepseek-v4-flash": "deepseek-flash",
    "deepseek-v4-flash-vision-exp": "deepseek-flash",
    "deepseek-v3.2": "deepseek-flash",
    "deepseek-chat": "deepseek-flash",
    "deepseek-coder": "deepseek-flash",
    "deepseek-reasoner": "deepseek-flash",
    "glm-5.2": "glm-5.3",
    "glm-5.1": "glm-5.3",
    "glm-4.7": "glm-5.3-flash",
    "glm-4-flash": "glm-5.3-flash",
    "glm-4": "glm-5.3-flash",
    "glm-3-turbo": "glm-5.3-flash",
    "grok-4.6": "grok-4.7",
    "grok-4.5": "grok-4.7",
    "grok-4.3": "grok-4.7",
    "grok-4.20-0309-reasoning": "grok-4.7",
    "grok-4.1-fast": "grok-4.7",
    "grok-3": "grok-4.7",
    "grok-3-mini": "grok-4.7",
    "grok-2": "grok-4.7",
    "qwen3.8-max-preview": "qwen3.8-max",
    "qwen3.7-max": "qwen3.8-max",
    "qwen3.6-plus": "qwen3.8-max",
    "qwen3.5-plus": "qwen3.8-max",
    "qwen3-max": "qwen3.8-max",
    "qwen-max": "qwen3.8-max",
    "qwen3-235b-a22b": "qwen3.8-max",
    "qwen-plus": "qwen3.8-max",
    "qwen3.6-35b-a3b": "qwen3.8-flash",
    "qwen3-32b": "qwen3.8-flash",
    "qwen-turbo": "qwen3.8-flash",
    "kimi-code/k3": "kimi-code/k3.1-pro",
    "kimi-code/k3-256k": "kimi-code/k3.1-pro",
    "kimi-code/kimi-for-coding": "kimi-code/k3.1-pro",
    "MiniMax-M3": "MiniMax-M3.1-Flash",
    "MiniMax-M2.7": "MiniMax-M3.1-Flash",
    "MiniMax-M2.5": "MiniMax-M3.1-Flash",
    "MiniMax-M2.1": "MiniMax-M3.1-Flash",
    "composer-2": null,
    "composer-2.5": null,
    "composer-1.5": null,
    "cursor": null,
    "nvidia/nemotron-3-super-120b-a12b:free": null,
    "kimi-k3": "kimi-k3.1-pro"
  },
  "model_tiers": {
    "_comment": "Model tiers for apply_model_tier() (mirrors get_model_for_tier in scripts/config.sh)",
    "maximum": {
      "claude": "claude-opus-5-5",
      "gemini": "gemini-4-argon-high",
      "codex": "gpt-6-astra",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3",
      "grok": "grok-4.7",
      "qwen3": "qwen3.8-max",
      "kimi": "kimi-code/k3.1-pro",
      "minimax": "MiniMax-M3.1-Flash",
      "meta": "muse-wonder-1.0"
    },
    "premium": {
      "claude": "claude-opus-5-5",
      "gemini": "gemini-4-argon-high",
      "codex": "gpt-6.1-sol",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.7",
      "qwen3": "qwen3.8-max",
      "kimi": "kimi-code/k3.1-pro",
      "minimax": "MiniMax-M3.1-Flash",
      "meta": "muse-wonder-1.0"
    },
    "standard": {
      "claude": "claude-opus-5-5",
      "gemini": "gemini-3.8-flash-high",
      "codex": "gpt-6.1-sol",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.7",
      "qwen3": "qwen3.8-flash",
      "kimi": "kimi-code/k3.1-pro",
      "minimax": "MiniMax-M3.1-Flash",
      "meta": "muse-spark-1.3"
    },
    "economy": {
      "claude": "claude-haiku-5-5",
      "gemini": "gemini-3.8-flash-low",
      "codex": "gpt-6-luna",
      "mistral": "mistral-medium-3.5",
      "deepseek": "deepseek-flash",
      "glm": "glm-5.3-flash",
      "grok": "grok-4.7",
      "qwen3": "qwen3.8-flash",
      "kimi": "kimi-code/k3.1-pro",
      "minimax": "MiniMax-M3.1-Flash",
      "meta": "muse-spark-1.3"
    }
  },
  "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-4-argon-high",
        "api": "gemini-4-argon"
      },
      "premium": {
        "cli": "gemini-4-argon-high",
        "api": "gemini-4-argon"
      },
      "standard": {
        "cli": "gemini-3.8-flash-high",
        "api": "gemini-3.8-flash"
      },
      "economy": {
        "cli": "gemini-3.8-flash-low",
        "api": "gemini-3.8-flash"
      }
    },
    "mistral": {
      "maximum": {
        "cli": "mistral-medium-3.5",
        "api": "mistral-large-4"
      },
      "premium": {
        "cli": "mistral-medium-3.5",
        "api": "mistral-large-4"
      },
      "standard": {
        "cli": "mistral-medium-3.5",
        "api": "mistral-large-4"
      },
      "economy": {
        "cli": "mistral-medium-3.5",
        "api": "mistral-large-4"
      }
    }
  },
  "consultant_fallbacks": {
    "_comment": "Premium defaults - 5.5.0",
    "claude": "claude-opus-5-5",
    "gemini": "gemini-4-argon-high",
    "codex": "gpt-6.1-sol",
    "mistral": "mistral-medium-3.5",
    "deepseek": "deepseek-flash",
    "glm": "glm-5.3-flash",
    "grok": "grok-4.7",
    "qwen3": "qwen3.8-max",
    "kimi": "kimi-code/k3.1-pro",
    "minimax": "MiniMax-M3.1-Flash",
    "meta": "muse-wonder-1.0"
  },
  "opt_in_targets": {
    "codex": [
      "gpt-6.1-terra"
    ],
    "gemini_cli": [
      "gemini-4-argon-medium",
      "gemini-4-argon-low",
      "gemini-3.8-flash-medium"
    ],
    "mistral_api": [
      "mistral-medium-3-5",
      "mistral-small-2603"
    ],
    "deepseek": [
      "deepseek-v4-pro"
    ],
    "claude": [
      "claude-fable-5-1"
    ],
    "meta": [
      "muse-spark-1.3-contributor"
    ]
  },
  "default_rate": {
    "input": 0.005,
    "output": 0.015
  }
}