{
  "_comment": "Canonical model catalog. Update this single file when a provider ships a new model. Providers/web-app/docs read from here.",
  "_source_of_truth": "models[] is authoritative. Each entry's `tier` decides what that tier resolves to, first match wins, so order within models[] is load-bearing. The top-level latest_<tier> keys are DERIVED mirrors kept only for existing readers (dashboard/server.py, tools/probe-model-catalog.py, tests); never hand-edit them out of step with models[] -- tests/test-model-catalog-single-source.sh fails when they disagree. A provider whose models[] has no entry for a tier must declare `tier_fallback` saying which tier substitutes; there is no implicit fallback.",
  "schema_version": 1,
  "updated": "2026-09-26",
  "providers": {
    "claude": {
      "cli": {
        "min_version": "2.1.0",
        "qualified_version": "2.1.293",
        "capabilities": ["stream-json", "permission-mode", "model-alias", "advisor"],
        "_comment": "Qualified CLI range for doctor. min_version is a hard floor (doctor fails below it). qualified_version is the newest release the compat probe has passed; a newer CLI warns as unqualified. Bump qualified_version only after the compat probe passes on the new release."
      },
      "latest_planning": "claude-opus-5-5",
      "latest_development": "claude-sonnet-5-5",
      "latest_fast": "claude-haiku-5-5",
      "cli_aliases": {
        "fable": "claude-fable-5-1",
        "opus": "claude-opus-5-5",
        "sonnet": "claude-sonnet-5-5",
        "haiku": "claude-haiku-5-5"
      },
      "models": [
        {
          "id": "claude-fable-5-1",
          "alias": "fable",
          "tier": "advisor",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive"]},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "high"},
          "notes": "Top-tier advisory model, released 2026-09-01. Pricing $10/$50 per MTok. Cache reads are 0.025x base input ($0.25/MTok), not the usual 0.1x. Doc-supported for architecture/root-cause; opt-in only (cost). Refuses cyber content, so NOT used for security review."
        },
        {
          "id": "claude-opus-5-5",
          "alias": "opus",
          "tier": "planning",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive"]},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "medium"},
          "notes": "Top model. Id confirmed 2026-09-26 by a real call (claude -p --model claude-opus-5-5, Claude Code 2.1.283, canonicalModel claude-opus-5-5); the CLI opus alias resolves to it."
        },
        {
          "id": "claude-opus-5",
          "tier": "planning",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive", "disabled"], "max_effort": {"disabled": "high"}},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "high"},
          "notes": "Superseded by claude-opus-5-5. Listed after it, so it is never the planning default (first match wins); not an alias target."
        },
        {
          "id": "claude-sonnet-5-5",
          "alias": "sonnet",
          "tier": "development",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive", "between_tools"], "max_effort": {"between_tools": "high"}, "substitute": {"disabled": "between_tools"}},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "high"},
          "notes": "Id confirmed 2026-10-07 by a real call (claude -p --model sonnet, Claude Code 2.1.293, modelUsage key claude-sonnet-5-5); the CLI sonnet alias resolves to it. ROUTER-1 R1-03."
        },
        {
          "id": "claude-sonnet-5",
          "tier": "legacy",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive", "disabled"]},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "high"},
          "notes": "Superseded by claude-sonnet-5-5 (catalog-only, not an alias target). Was the default execution model as of v7.104.0. Intro price $2/$10 per MTok through 2026-08-31; list price $3/$15 per MTok."
        },
        {
          "id": "claude-haiku-5-5",
          "alias": "haiku",
          "tier": "fast",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive", "disabled"], "max_effort": {"disabled": "high"}},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "medium"},
          "notes": "Id confirmed 2026-10-07 by a real call (claude -p --model haiku, Claude Code 2.1.293, modelUsage key claude-haiku-5-5); the CLI haiku alias resolves to it. ROUTER-1 R1-03. Context window 1M and max_output 128k per the Anthropic docs snapshot 2026-10 (context-windows.md:38, thinking.md:1217)."
        },
        {
          "id": "claude-haiku-4-5",
          "tier": "legacy",
          "context_window": 200000,
          "max_output": 64000,
          "thinking": {"types": ["enabled", "disabled"]},
          "effort": {"levels": []},
          "notes": "Superseded by claude-haiku-5-5. Catalog-only, not an alias target; exact-id pricing keeps it at its own rate."
        },
        {
          "id": "claude-fable-5",
          "tier": "legacy",
          "context_window": 1000000,
          "max_output": 128000,
          "thinking": {"types": ["adaptive"]},
          "effort": {"levels": ["low", "medium", "high", "xhigh", "max"], "default": "high"},
          "notes": "Superseded by claude-fable-5-1 (2026-09-01). Catalog-only; not a latest_* or alias target."
        }
      ]
    },
    "codex": {
      "latest_planning": "gpt-5.6-sol",
      "latest_development": "gpt-5.6-terra",
      "latest_fast": "gpt-5.6-luna",
      "models": [
        {
          "id": "gpt-5.6-sol",
          "tier": "planning",
          "notes": "high tier. OpenAI: 'Frontier model for complex professional work'. Verified against developers.openai.com/api/docs/models."
        },
        {
          "id": "gpt-5.6-terra",
          "tier": "development",
          "notes": "medium tier, the DEFAULT. OpenAI: balances performance with affordability."
        },
        {
          "id": "gpt-5.6-luna",
          "tier": "fast",
          "notes": "small tier. OpenAI: budget-conscious, high-volume."
        },
        {
          "id": "gpt-5.3-codex",
          "tier": "legacy",
          "notes": "Prior default, superseded by the gpt-5.6 line. Kept discoverable, not dispatched."
        },
        {
          "id": "o3",
          "tier": "planning",
          "notes": "Alternative planning model. NOT the default -- gpt-5.3-codex is listed first and first match wins."
        },
        {
          "id": "o4-mini",
          "tier": "legacy",
          "notes": "Was tier=fast, which made the cheap tier resolve to o4-mini while latest_fast said gpt-5.3-codex. Codex does not differentiate tiers by model, so it is not any tier's default; parked at tier=legacy so it stays discoverable without being dispatched."
        }
      ],
      "notes": "Codex uses a single model with effort level (xhigh/high/low) for tier differentiation, so development and fast declare an explicit tier_fallback to planning rather than naming separate models."
    },
    "cline": {
      "effort": {"flag": null, "levels": [], "unsupported": true, "cli": "cline (not installed here; its documented flags -y and -m include no effort or reasoning option)", "_comment": "Cline exposes no effort or reasoning flag, so LOKI_EFFORT is recorded as unsupported and no flag is emitted."},
      "latest_planning": "openrouter/deepseek/deepseek-v3.2",
      "latest_development": "openrouter/deepseek/deepseek-v3.2",
      "latest_fast": "openrouter/deepseek/deepseek-chat",
      "models": [
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "planning",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-chat",
          "tier": "fast",
          "open_weights": true
        },
        {
          "id": "openrouter/z-ai/glm-4.6",
          "tier": "development",
          "open_weights": true
        }
      ]
    },
    "aider": {
      "effort": {"flag": "--reasoning-effort", "levels": ["low", "medium", "high"], "default": "medium", "cli": "aider 0.86.2", "_comment": "Verified from aider --help (--reasoning-effort sets the reasoning_effort API parameter). A model entry may carry its own effort block, which wins over this provider default."},
      "latest_planning": "openrouter/deepseek/deepseek-v3.2",
      "latest_development": "openrouter/deepseek/deepseek-v3.2",
      "latest_fast": "openrouter/deepseek/deepseek-chat",
      "models": [
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "planning",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-chat",
          "tier": "fast",
          "open_weights": true
        },
        {
          "id": "openrouter/minimax/minimax-m2.1",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "ollama_chat/deepseek-coder",
          "tier": "fast",
          "open_weights": true
        }
      ]
    },
    "opencode": {
      "effort": {"flag": "--variant", "levels": ["low", "medium", "high"], "default": "medium", "cli": "opencode 1.18.9", "_comment": "Verified from opencode run --help (--variant: provider-specific reasoning effort). A model entry may carry its own effort block, which wins over this provider default."},
      "latest_planning": "openrouter/deepseek/deepseek-v3.2",
      "latest_development": "openrouter/deepseek/deepseek-v3.2",
      "latest_fast": "openrouter/deepseek/deepseek-chat",
      "models": [
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "planning",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "openrouter/deepseek/deepseek-chat",
          "tier": "fast",
          "open_weights": true
        },
        {
          "id": "openrouter/z-ai/glm-4.6",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "openrouter/minimax/minimax-m2.1",
          "tier": "development",
          "open_weights": true
        },
        {
          "id": "ollama/qwen2.5-coder",
          "tier": "fast",
          "open_weights": true
        }
      ]
    },
    "generic": {
      "_comment": "Fallback for ANY provider not named above (bring-your-own endpoint). All three tiers collapse to one open model, the same shape codex uses, declared via tier_fallback. Override per tier with LOKI_<PROVIDER>_MODEL_<TIER> or wholesale with LOKI_<PROVIDER>_MODEL.",
      "latest_planning": "openrouter/deepseek/deepseek-v3.2",
      "latest_development": "openrouter/deepseek/deepseek-v3.2",
      "latest_fast": "openrouter/deepseek/deepseek-v3.2",
      "tier_fallback": {
        "planning": "development",
        "fast": "development"
      },
      "models": [
        {
          "id": "openrouter/deepseek/deepseek-v3.2",
          "tier": "development",
          "open_weights": true
        }
      ]
    },
    "minimax": {
      "_comment": "Catalog-only compatibility metadata. MiniMax is not a fifth --provider value; select these models through the existing Claude or Aider adapters with the matching endpoint variables.",
      "latest_planning": "MiniMax-M3",
      "latest_development": "MiniMax-M2.7",
      "latest_fast": "MiniMax-M2.7",
      "tier_fallback": {
        "fast": "development"
      },
      "endpoints": [
        {
          "region": "global_en",
          "openai_base_url": "https://api.minimax.io/v1",
          "anthropic_base_url": "https://api.minimax.io/anthropic",
          "docs_root": "https://platform.minimax.io/docs"
        },
        {
          "region": "cn_zh",
          "openai_base_url": "https://api.minimaxi.com/v1",
          "anthropic_base_url": "https://api.minimaxi.com/anthropic",
          "docs_root": "https://platform.minimaxi.com/docs"
        }
      ],
      "models": [
        {
          "id": "MiniMax-M3",
          "tier": "planning",
          "context_window": 1000000,
          "input_modalities": [
            "text",
            "image",
            "video"
          ],
          "thinking": [
            "adaptive",
            "disabled"
          ],
          "pricing_usd_per_million_tokens": {
            "input": 0.3,
            "output": 1.2,
            "cache_read": 0.06,
            "cache_write": null
          },
          "pricing_tiers_usd_per_million_tokens": [
            {
              "service_tier": "standard",
              "input_tokens_lte": 512000,
              "input": 0.3,
              "output": 1.2,
              "cache_read": 0.06,
              "cache_write": null
            },
            {
              "service_tier": "standard",
              "input_tokens_gt": 512000,
              "input": 0.6,
              "output": 2.4,
              "cache_read": 0.12,
              "cache_write": null
            },
            {
              "service_tier": "priority",
              "input_tokens_lte": 512000,
              "input": 0.45,
              "output": 1.8,
              "cache_read": 0.09,
              "cache_write": null
            },
            {
              "service_tier": "priority",
              "input_tokens_gt": 512000,
              "input": 0.9,
              "output": 3.6,
              "cache_read": 0.18,
              "cache_write": null
            }
          ]
        },
        {
          "id": "MiniMax-M2.7",
          "tier": "development",
          "context_window": 204800,
          "input_modalities": [
            "text"
          ],
          "thinking": [
            "always_on"
          ],
          "pricing_usd_per_million_tokens": {
            "input": 0.3,
            "output": 1.2,
            "cache_read": 0.06,
            "cache_write": 0.375
          }
        }
      ]
    }
  }
}