From 2f7541040f383bae7472f01d99b054d1cd085aa1 Mon Sep 17 00:00:00 2001 From: proxmenux-bot Date: Wed, 2 Sep 2026 08:30:04 +0000 Subject: [PATCH] chore(ai-models): daily catalog refresh --- AppImage/config/verified_ai_models.json | 136 ++++++++++++++++-------- 1 file changed, 94 insertions(+), 42 deletions(-) diff --git a/AppImage/config/verified_ai_models.json b/AppImage/config/verified_ai_models.json index 85077cbc..965a6d88 100644 --- a/AppImage/config/verified_ai_models.json +++ b/AppImage/config/verified_ai_models.json @@ -1,85 +1,137 @@ { "_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", + "_updated": "2026-09-02", "_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" + "allam-2-7b", + "qwen/qwen3.8-27b", + "groq/compound-mini", + "groq/compound" ], - "recommended": "llama-3.3-70b-versatile", + "recommended": "allam-2-7b", "_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-3.1-flash-lite-preview", + "gemini-2.5-flash", + "gemini-3.5-flash-lite", + "gemini-flash-lite-latest", "gemini-3-flash-preview", - "gemini-3.5-flash" + "gemini-3.5-flash", + "gemini-3.7-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"] + "_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-nano-2025-04-14", + "gpt-4.1-2025-04-14", + "gpt-5-nano-2025-08-07", "gpt-4.1", - "gpt-4o", - "gpt-5-chat-latest", - "gpt-5-nano" + "gpt-4o-2024-11-20", + "gpt-4o-2024-05-13", + "gpt-5-nano", + "gpt-4.1-mini", + "gpt-4.1-mini-2025-04-14", + "gpt-4o-mini", + "gpt-4o-mini-2024-07-18", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-1106", + "gpt-5", + "gpt-3.5-turbo", + "gpt-4", + "gpt-4-0613", + "gpt-4o-2024-08-06", + "gpt-4-turbo-2024-04-09", + "gpt-4-turbo", + "gpt-4o" ], "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-haiku-4-5-20251001", "claude-opus-4-8", + "claude-opus-4-5-20251101", + "claude-opus-4-7", + "claude-fable-5", + "claude-sonnet-4-5-20250929", "claude-sonnet-4-6", - "claude-opus-4-6", - "claude-fable-5" + "claude-fable-5-1", + "claude-opus-4-6" ], - "recommended": "claude-haiku-4-5", + "recommended": "claude-haiku-4-5-20251001", "_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", + "tencent/hy-mt2-1.8b", + "amazon/nova-2-lite-v1", + "google/gemini-3.1-flash-lite-preview", + "inclusionai/ling-3.0-flash", + "rekaai/reka-edge", + "tencent/hy-mt2-7b", + "google/gemini-3.5-flash-lite", + "tencent/hy-mt2-30b-a3b", + "google/gemini-3.1-flash-lite", + "~openai/gpt-mini-latest", + "openai/gpt-5.4-nano", + "mistralai/mistral-small-2603", + "poolside/laguna-s-2.1", + "ibm-granite/granite-4.1-8b", + "deepseek/deepseek-v4-flash-vision-exp", + "nex-agi/nex-n2-pro", + "x-ai/grok-4.20", + "openai/gpt-5.6-terra", + "google/gemma-4-26b-a4b-it", + "google/gemma-4-31b-it", "nvidia/nemotron-3-super-120b-a12b:free", - "google/gemma-4-26b-a4b-it:free", - "nvidia/nemotron-nano-12b-v2-vl:free", - "nvidia/nemotron-3-nano-30b-a3b:free", + "liquid/lfm-2.5-2.6b:free", + "~openai/gpt-latest", + "openai/gpt-5.6-luna", + "inclusionai/ling-3.0-flash-fin:free", + "~anthropic/claude-haiku-latest", + "z-ai/glm-5.3", + "openai/gpt-5.6-sol", + "~anthropic/claude-sonnet-latest", + "anthropic/claude-opus-5", + "perceptron/perceptron-mk1", + "aion-labs/aion-3.0-mini", + "x-ai/grok-4.3", + "anthropic/claude-fable-5.1", + "minimax/minimax-m2.7", "poolside/laguna-s-2.1:free", + "openai/gpt-5.6-luna-pro", + "openai/gpt-5.6-terra-pro", + "minimax/minimax-m3:free", + "openai/gpt-5.6-sol-pro", "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", - "openai/gpt-oss-20b:free" + "x-ai/grok-4.6", + "upstage/solar-pro4", + "deepseek/deepseek-v4-flash", + "qwen/qwen3.8-27b", + "x-ai/grok-4.20-multi-agent", + "x-ai/grok-build-0.1", + "qwen/qwen3.6-max-preview" ], - "recommended": "meta-llama/llama-3.3-70b-instruct", + "recommended": "tencent/hy-mt2-1.8b", "_note": "Paid tier 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). Free tier verified 2026-08-17 — 7 :free models pass and are appended, ordered by latency: nemotron-3-super-120b-a12b (3.5s), gemma-4-26b-a4b-it (4.1s), nemotron-nano-12b-v2-vl (5.3s), nemotron-3-nano-30b-a3b (5.8s), laguna-s-2.1 (8.3s), nemotron-3-nano-omni-30b-a3b-reasoning (10.7s), gpt-oss-20b (12.2s). Free-tier rate limits (~20 req/min shared across all OpenRouter free users on that model) may cause 429 in high-traffic windows — usable for occasional notification translation, not for high-volume automation. 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": [],