ProxMenux/AppImage/config/verified_ai_models.json

{
  "_description": "Verified AI models for ProxMenux notifications. Only models listed here will be shown to users. Models are tested to work with the chat/completions API format.",
  "_updated": "2026-07-14",
  "_verifier": "Refreshed with tools/ai-models-verifier (private). Re-run before each ProxMenux release to keep the list current. The verifier and ProxMenux share the same reasoning/thinking-model handlers so their verdicts stay aligned with runtime behaviour.",

  "groq": {
    "models": [
      "llama-3.3-70b-versatile",
      "llama-3.1-8b-instant",
      "meta-llama/llama-4-scout-17b-16e-instruct",
      "openai/gpt-oss-120b",
      "openai/gpt-oss-20b"
    ],
    "recommended": "llama-3.3-70b-versatile",
    "_note": "Verified functionally 2026-07-14 with the Groq API (15 models discovered, 9 passed). Legacy llama-3.1-70b-versatile / llama3-70b-8192 / llama3-8b-8192 / mixtral-8x7b-32768 / gemma2-9b-it removed (retired upstream). llama-4-scout added (current-gen Llama 4, 0.47s). openai/gpt-oss-120b / gpt-oss-20b confirmed. Passing but excluded: allam-2-7b (Arabic-focused), qwen/qwen3-32b (Chinese-first, unreliable Spanish output), openai/gpt-oss-safeguard-20b (safety-classifier variant), groq/compound-mini (agentic system, wrong fit for notification translation)."
  },

  "gemini": {
    "models": [
      "gemini-flash-lite-latest",
      "gemini-2.5-flash-lite",
      "gemini-2.5-flash",
      "gemini-3.1-flash-lite",
      "gemini-3-flash-preview",
      "gemini-3.5-flash"
    ],
    "recommended": "gemini-2.5-flash-lite",
    "_note": "Verified 2026-07-13. gemini-flash-lite-latest now passes consistently (1.6s) and is fastest, but gemini-2.5-flash-lite remains recommended because 'latest' aliases can drift over time. gemini-3.1-flash-lite is the stable successor to 3-flash-preview. Pro variants continue to reject thinkingBudget=0 and are overkill for notification translation.",
    "_deprecated": ["gemini-2.0-flash", "gemini-2.0-flash-lite", "gemini-1.5-flash", "gemini-1.0-pro", "gemini-pro"]
  },

  "openai": {
    "models": [
      "gpt-4.1-nano",
      "gpt-4.1-mini",
      "gpt-4o-mini",
      "gpt-4.1",
      "gpt-4o",
      "gpt-5-chat-latest",
      "gpt-5-nano"
    ],
    "recommended": "gpt-4.1-nano",
    "_note": "Verified 2026-07-13. gpt-5.4-nano / gpt-5.4-mini removed (HTTP 400 — provider params rejected). gpt-5-nano added (2.0s, current-gen fast). Reasoning models (o-series, gpt-5/5.1/5.2 non-chat variants) are supported by openai_provider.py via max_completion_tokens + reasoning_effort=minimal, but not listed here: their latency is higher and they do not improve translation quality for notifications. Add specific reasoning IDs to this list only if a user explicitly wants them."
  },

  "anthropic": {
    "models": [
      "claude-haiku-4-5",
      "claude-sonnet-5",
      "claude-opus-4-8",
      "claude-sonnet-4-6",
      "claude-opus-4-6",
      "claude-fable-5"
    ],
    "recommended": "claude-haiku-4-5",
    "_note": "Verified 2026-07-13 with all 10 discovered models passing after aligning the verifier with anthropic_provider.py (temperature omitted — newest generations reject it with 'temperature is deprecated for this model'). Legacy claude-3-5-haiku-latest / claude-3-5-sonnet-latest / claude-3-opus-latest removed (deprecated upstream, not in the Models API). haiku-4-5 is the sweet spot for notification translation (3.6s, $1/$5 per MTok); sonnet-5 for slightly richer output (3.1s, $3/$15); opus-4-8 / fable-5 for demanding cases."
  },

  "openrouter": {
    "models": [
      "meta-llama/llama-3.3-70b-instruct",
      "meta-llama/llama-3.1-70b-instruct",
      "meta-llama/llama-3.1-8b-instruct",
      "meta-llama/llama-4-scout",
      "anthropic/claude-haiku-4.5",
      "anthropic/claude-sonnet-4.6",
      "google/gemini-2.5-flash-lite",
      "google/gemini-2.5-flash",
      "openai/gpt-4o-mini",
      "mistralai/mistral-small-3.2-24b-instruct"
    ],
    "recommended": "meta-llama/llama-3.3-70b-instruct",
    "_note": "Verified functionally 2026-07-14 with the OpenRouter API — all 10 curated candidates pass the Spanish-translation notification test. Fastest: llama-4-scout (0.51s), gemini-2.5-flash-lite (1.14s), gemini-2.5-flash (1.94s), llama-3.3-70b-instruct (2.29s), claude-haiku-4.5 (2.71s). Legacy anthropic/claude-3.5-* / google/gemini-flash-1.5 / mistralai/mistral-7b-instruct / mixtral-8x7b-instruct removed (GONE from catalog). Modern replacements added: llama-4-scout (Meta's current gen — dramatically fastest), claude-haiku-4.5 / claude-sonnet-4.6, gemini-2.5-flash / flash-lite, mistral-small-3.2-24b. recommended kept as llama-3.3-70b for capability/latency balance; llama-4-scout is a faster alternative worth considering as recommended after a broader release."
  },

  "ollama": {
    "_note": "Ollama models are local, we don't filter them. User manages their own models.",
    "models": [],
    "recommended": ""
  }
}