Elorian: Glimpse

{"about":"### 推理事件與空間關係\n\nGlimpse 是 Elorian 以理解物理世界的視覺資訊為核心設計的模型。它著重在物件移動及視角改變時持續掌握同一物件、連結動作與後果，以及分析場景各部分的關係。開發商的官方範例展示了動作分析、考量狀態的物件計數，以及事件順序還原。\n\nGlimpse 的特色概念是在解題過程中回頭檢視視覺證據。在 Elorian 環境中，模型可再次查看所需區域、比對觀察並修正最初解讀。這說明它為何專注於不能只說出物件名稱的工作：還需要理解哪些部分改變、哪些物件仍是同一個，以及觀察與假設有何差別。\n\n### 在 Ailoot 中如何使用\n\nAiloot 的 Glimpse 連線接受文字輸入並傳回文字答案。可以提供場景描述、觀察序列、事件逐字紀錄或準備好的圖說，再根據這些資料提問。目前此模型介面不處理影像或影片本身。\n\n實際請求可包含觀察紀錄：誰在何時做了什麼，以及動作前後看見了什麼。要求模型整理時間軸、區分可觀察事實與可能解釋，再列出做出結論仍缺少的細節。這種形式可透過文字表徵處理任務，並清楚保留已提供資訊與解讀之間的界線。\n\n### 提問時應注意什麼\n\n空間問題適合註明觀察位置並描述物件的相對位置。事件序列則應保留時間戳記與一致的參與者稱呼。若原文未說明兩次觀察之間是否持續移動，宜要求模型考慮合理的可能情況，而非直接選定唯一解釋。\n\nAiloot 的 Glimpse 標示上下文為 262,144 個 token，可在請求中放入大量描述及討論歷史。結果仍為文字，例如解釋、事件表或針對原始資料的問題清單。Elorian 代理環境的能力，包括視覺工具與子任務協調，不應自動視為此文字介面所具備。","alias_of":null,"aliases":[],"author":"Elorian","canonical_model":"elorian/glimpse","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"elorian/glimpse","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.12,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"anthropic","fast_multiplier":1,"flex_multiplier":1,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":1.2,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/messages","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":1.2,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/responses","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":1.2,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.12,"cache_write":null,"cache_write_1h":null,"cache_write_5m":null,"conditional_meter":null,"ctx":null,"family":"gemini","fast_multiplier":1,"flex_multiplier":1,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":1.2,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":6.0,"output":["text"],"path":"/v1beta/models/elorian/glimpse:generateContent","request_model_id":"elorian/glimpse","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"elorian/glimpse","request_model_id":"elorian/glimpse","route_label":"Ultra"}],"name":"Elorian: Glimpse","price":{"in":1.2,"in_label":null,"out":6.0,"out_label":null,"sort_in":1.2,"sort_out":6.0,"varies":false},"public_id":"elorian/glimpse","short":"Elorian 的場景與物理事件推理模型；在 Ailoot 中以文字描述與問題進行互動。"}