Moondream: Moondream 3.1

{"about":"### Moondream 3.1 與可觀察資料的對應\n\nMoondream 3.1 是採用專家混合架構的 Moondream 視覺語言模型版本。開發商標示總計 90 億參數，每個 token 啟用約 20 億參數。此版本主要著重與影像中特定物件及區域相連的答案：除了描述場景，也要指出結果對應至哪個部分。\n\n原始模型的官方模型卡區分五種技能：影像問答、圖說、物件偵測、點位標示與分割。問答產生文字解釋；偵測將物件與矩形區域連結；點位標示其位置；分割則標出所占區域。需要特定結果類型，而非整張影像自由描述的系統，可運用這種方式。\n\n### Ailoot 提供的模式\n\n在 Ailoot，Moondream 3.1 連線接受文字訊息並傳回文字答案。目前模型卡的介面不包含影像處理，也不透過這些專用技能輸出視覺座標或遮罩。文字任務可提供準備好的觀察描述、特徵表或結果要求，再據此提問。\n\n例如，若商品或物件資訊已整理成文字，可圍繞明確標準建立請求：比較哪些特徵、何者算符合，以及如何標記缺少的值。要求保留名稱及原始數值，並根據提供資料為結論附上簡短說明。這是在處理觀察的文字紀錄，不能取代檢視原始照片。\n\n### 上下文與結果界線\n\nAiloot 為此版本標示 32,000 個 token 的上下文。請求可包含指示、所需格式的範例及待處理資料。若任務要求明確選擇，可事先限定可接受答案並提供判準，讓題目能被驗證，而不必猜測輸入缺少哪些資訊。\n\nMoondream 專注視覺理解，不代表所有數值或邏輯結論都會自動正確。開發商在官方模型卡中，將偵測與空間對應任務和一般文字數學任務分開描述。選擇此版本時應考量具體輸入及所需答案；Ailoot 目前此連線的結果仍為文字。","alias_of":null,"aliases":[],"author":"Moondream","canonical_model":"moondream/moondream3.1-9b-a2b","ctx":null,"formats":["chat","gemini","messages","responses"],"id":"moondream/moondream3.1-9b-a2b","input":["text"],"kind":"text","max_out":null,"methods":[{"cache_read":null,"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":0.6,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/messages","request_model_id":"moondream/moondream3.1-9b-a2b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":null,"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":0.6,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/responses","request_model_id":"moondream/moondream3.1-9b-a2b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":null,"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":0.6,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"moondream/moondream3.1-9b-a2b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":null,"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":0.6,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1beta/models/moondream/moondream3.1-9b-a2b:generateContent","request_model_id":"moondream/moondream3.1-9b-a2b","route_label":"Ultra","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"moondream/moondream3.1-9b-a2b","request_model_id":"moondream/moondream3.1-9b-a2b","route_label":"Ultra"}],"name":"Moondream: Moondream 3.1","price":{"in":0.6,"in_label":null,"out":5.0,"out_label":null,"sort_in":0.6,"sort_out":5.0,"varies":false},"public_id":"moondream/moondream3.1-9b-a2b","short":"Moondream 3.1 著重將答案精確對應至場景物件；在 Ailoot 中提供文字使用模式。"}