Inception: Mercury 3

{"about":"### 採用擴散技術的文字模型\n\nMercury 3 是 Inception 採用擴散方法生成文字的模型。它延續 Mercury 家族，開發商將這個家族用於互動應用，以及需要連續多次呼叫模型的工作。Inception 對 Mercury 3 的描述著重對話支援、教學、資料工作與搜尋代理情境。\n\n擴散架構是模型的特性，並不決定特定應用程式的回應時間；最終時間也取決於請求大小、結果長度與服務條件。在 Ailoot，Mercury 3 接受文字並傳回文字。此介面適合說明、文件處理，以及根據提供資訊準備下一個工作步驟。\n\n### 以大型上下文串連工作\n\nAiloot 的 Mercury 3 標示上下文為 1,000,000 個 token，可在同一次討論中放入大型文字資料集，例如產品說明、規則、往來訊息及輸出要求。當答案必須同時考量任務的多個部分時，大型上下文便有實際價值，例如比對客服指引與合約條款，再針對特定詢問準備回覆。\n\n這類請求適合清楚標示文件並保留名稱，要求每項結論註明所依據的資料。若任務有數個步驟，請指定中間結果：先列相關規則，再分析個案，最後準備回覆草稿。這能讓結果更易檢查，也能只針對一個階段追問，而不必重新描述整個任務。\n\n### 互動使用情境\n\n在教學對話中，可用 Mercury 3 分析解題過程、提供提示，或依指定程度解釋概念。處理資料時，可提供欄位說明、文字形式的樣本與問題，以取得規律說明或轉換計畫。客服情境則可附上規則，要求根據使用者情況撰寫清楚回覆。\n\n這些情境將文字模型作為工作流程的一部分。自主上網搜尋、操作瀏覽器、存取公司系統及語音對話，都取決於應用程式所連接的工具。Mercury Voice 與 Mercury Decide 是 Inception 的獨立產品，其專用能力不屬於 Mercury 3 的說明範圍。","alias_of":null,"aliases":[],"author":"Inception","canonical_model":"inception/mercury-3","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"inception/mercury-3","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":0.02,"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":0.2,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/messages","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"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":0.2,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/responses","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"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":0.2,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1/chat/completions","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.02,"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":0.2,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":0.7,"output":["text"],"path":"/v1beta/models/inception/mercury-3:generateContent","request_model_id":"inception/mercury-3","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"inception/mercury-3","request_model_id":"inception/mercury-3","route_label":"Ultra"}],"name":"Inception: Mercury 3","price":{"in":0.2,"in_label":null,"out":0.7,"out_label":null,"sort_in":0.2,"sort_out":0.7,"varies":false},"public_id":"inception/mercury-3","short":"Inception 的擴散式文字模型，用於對話、大型文件處理與連續多步驟的知識工作。"}