Source: https://ailoot.ai/models/zh-hant-tw/openai-gpt-6-1-terra/ Canonical: https://ailoot.ai/models/zh-hant-tw/openai-gpt-6-1-terra/ Language: zh-hant-tw # OpenAI: GPT-6.1 Terra [Markdown](https://ailoot.ai/models/zh-hant-tw/openai-gpt-6-1-terra/index.md) · [JSON](https://ailoot.ai/models/zh-hant-tw/openai-gpt-6-1-terra/facts.json) ## [OpenAI: GPT-6.1 Terra](https://ailoot.ai/models/zh-hant-tw/openai-gpt-6-1-terra/) `openai/gpt-6.1-terra` OpenAI文字輸入 from US$0.001 / 1K輸出 from US$0.005 / 1K GPT-6.1 Terra 用於撰寫與編輯清楚文字、分析文件，以及在大型上下文中整理資料。 ### 模型用途 GPT-6.1 Terra 是 OpenAI 的推理模型，著重清楚、自然的文字。開發商也將它用於發展視覺分析及介面操作能力。在 Ailoot API，本模型卡供文字請求使用：提供原始資料後，可取得說明、改寫文字或依指定結構呈現的答案。 ### 文字、文件與工作資料 Terra 可用於編輯流程：依重點準備草稿、調整語氣、縮短篇幅，或將零散筆記整理為連貫文件。為取得合適結果，請指定讀者與文字目的，列出必要資訊，並註明必須保留的措辭。需要數個版本時，可要求只改變特定參數，例如詳細程度或對不同讀者的呈現方式。 處理文件時，適合將原文與問題一併提供。可要求逐節摘要、比對兩個版本，或將資訊擷取至事先定義的欄位清單。比較資料時，請指定標準：什麼算相符、哪些差異重要，以及如何呈現結果。這能讓模型取得清楚任務，也便於將結果與原文核對。 ### Ailoot API 提供的格式 輸入為文字，輸出也為文字。本模型卡支援的介面包括 Messages、Responses、Chat Completions 及 Gemini 相容的 generateContent。選擇客戶端使用的格式，透過該格式傳入指示與原始資料。若任務涉及文件或影像，此文字情境需使用預先擷取的文字或文字描述。 ### 工作流程範例 1. 提供筆記、草稿或文件文字。 2. 說明任務：編輯、解釋、比較或整理結構。 3. 指定讀者、限制與答案結構。 4. 依原始資料檢查結果，再針對需要不同詳細程度的部分追問。 此流程適合操作說明、內部參考資料、描述及分析筆記，尤其重視清楚表達與運用已提供資料的工作。 ### 可透過 Ailoot API 使用 輸入 `text` 輸出 `text` 上下文 272,000 *token* 最大回應 128,000 *token* 輸入 US$0.001 */ 1K* 輸出 US$0.005 */ 1K* 讀取快取 US$0.00005 */ 1K* 寫入快取 US$0.00125 */ 1K* 寫入快取，5 分鐘 US$0.00125 */ 1K token* fast 倍率 ×2 flex 倍率 ×0.5 輸入 `text` 輸出 `text` 上下文 272,000 *token* 最大回應 128,000 *token* 輸入 US$0.001 */ 1K* 輸出 US$0.005 */ 1K* 讀取快取 US$0.00005 */ 1K* 寫入快取 US$0.00125 */ 1K* 寫入快取，5 分鐘 US$0.00125 */ 1K token* fast 倍率 ×2 flex 倍率 ×0.5 輸入 `text` 輸出 `text` 上下文 272,000 *token* 最大回應 128,000 *token* 輸入 US$0.001 */ 1K* 輸出 US$0.005 */ 1K* 讀取快取 US$0.00005 */ 1K* 寫入快取 US$0.00125 */ 1K* 寫入快取，5 分鐘 US$0.00125 */ 1K token* fast 倍率 ×2 flex 倍率 ×0.5 輸入 `text` 輸出 `text` 上下文 272,000 *token* 最大回應 128,000 *token* 輸入 US$0.001 */ 1K* 輸出 US$0.005 */ 1K* 讀取快取 US$0.00005 */ 1K* 寫入快取 US$0.00125 */ 1K* 寫入快取，5 分鐘 US$0.00125 */ 1K token* fast 倍率 ×2 flex 倍率 ×0.5 輸入 `text` 輸出 `text` 上下文 922,000 *token* 最大回應 128,000 *token* 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* #### 依請求長度計價 · OpenAI Chat | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 922,000 *token* 最大回應 128,000 *token* 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* #### 依請求長度計價 · OpenAI Responses | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 922,000 *token* 最大回應 128,000 *token* 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* #### 依請求長度計價 · Gemini generateContent | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 型錄未列明 最大回應 型錄未列明 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* web\_search\_call US$0.02 *每次呼叫* #### 依請求長度計價 · Anthropic Messages | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 型錄未列明 最大回應 型錄未列明 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* web\_search\_call US$0.02 *每次呼叫* #### 依請求長度計價 · OpenAI Responses | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 型錄未列明 最大回應 型錄未列明 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* web\_search\_call US$0.02 *每次呼叫* #### 依請求長度計價 · OpenAI Chat | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 輸入 `text` 輸出 `text` 上下文 型錄未列明 最大回應 型錄未列明 輸入 US$0.002 */ 1K* 輸出 US$0.01 */ 1K* 讀取快取 US$0.0001 */ 1K* 寫入快取 US$0.0025 */ 1K* 寫入快取，5 分鐘 US$0.0025 */ 1K token* 寫入快取，1 小時 US$0.0025 */ 1K token* web\_search\_call US$0.02 *每次呼叫* #### 依請求長度計價 · Gemini generateContent | 請求大小，tokens | 輸入 | 輸出 | 讀取快取 | 寫入快取 | 快取 5 分鐘 | 快取 1 小時 | | --- | --- | --- | --- | --- | --- | --- | | 請求大小，tokens(0; 272,000\] | 輸入US$0.002 | 輸出US$0.01 | 讀取快取US$0.0001 | 寫入快取US$0.0025 | 快取 5 分鐘US$0.0025 | 快取 1 小時US$0.0025 | | 請求大小，tokens(272,000; ∞) | 輸入US$0.004 | 輸出US$0.015 | 讀取快取US$0.0002 | 寫入快取US$0.005 | 快取 5 分鐘US$0.005 | 快取 1 小時US$0.005 | 費率單位為每 1K Token 的 USD 金額。 未設定費率時，會沿用此方法的基本費率；«—» 表示未設定基本費率。 `openai/gpt-6.1-terra` · JSON ``` {"about":"### 模型用途\nGPT-6.1 Terra 是 OpenAI 的推理模型，著重清楚、自然的文字。開發商也將它用於發展視覺分析及介面操作能力。在 Ailoot API，本模型卡供文字請求使用：提供原始資料後，可取得說明、改寫文字或依指定結構呈現的答案。\n\n### 文字、文件與工作資料\nTerra 可用於編輯流程：依重點準備草稿、調整語氣、縮短篇幅，或將零散筆記整理為連貫文件。為取得合適結果，請指定讀者與文字目的，列出必要資訊，並註明必須保留的措辭。需要數個版本時，可要求只改變特定參數，例如詳細程度或對不同讀者的呈現方式。\n\n處理文件時，適合將原文與問題一併提供。可要求逐節摘要、比對兩個版本，或將資訊擷取至事先定義的欄位清單。比較資料時，請指定標準：什麼算相符、哪些差異重要，以及如何呈現結果。這能讓模型取得清楚任務，也便於將結果與原文核對。\n\n### Ailoot API 提供的格式\n輸入為文字，輸出也為文字。本模型卡支援的介面包括 Messages、Responses、Chat Completions 及 Gemini 相容的 generateContent。選擇客戶端使用的格式，透過該格式傳入指示與原始資料。若任務涉及文件或影像，此文字情境需使用預先擷取的文字或文字描述。\n\n### 工作流程範例\n1. 提供筆記、草稿或文件文字。\n2. 說明任務：編輯、解釋、比較或整理結構。\n3. 指定讀者、限制與答案結構。\n4. 依原始資料檢查結果，再針對需要不同詳細程度的部分追問。\n\n此流程適合操作說明、內部參考資料、描述及分析筆記，尤其重視清楚表達與運用已提供資料的工作。","alias_of":null,"aliases":["gpt-6.1-terra"],"author":"OpenAI","canonical_model":"openai/gpt-6.1-terra","ctx":922000,"formats":["chat","gemini","messages","responses"],"id":"openai/gpt-6.1-terra","input":["text"],"kind":"text","max_out":128000,"methods":[{"cache_read":0.05,"cache_write":1.25,"cache_write_1h":null,"cache_write_5m":1.25,"conditional_meter":null,"ctx":272000,"family":"anthropic","fast_multiplier":2,"flex_multiplier":0.5,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":1.0,"input":["text"],"label":"Anthropic Messages","max_out":128000,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/messages","request_model_id":"gpt-6.1-terra","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.05,"cache_write":1.25,"cache_write_1h":null,"cache_write_5m":1.25,"conditional_meter":null,"ctx":272000,"family":"openai","fast_multiplier":2,"flex_multiplier":0.5,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":1.0,"input":["text"],"label":"OpenAI Responses","max_out":128000,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/responses","request_model_id":"gpt-6.1-terra","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.05,"cache_write":1.25,"cache_write_1h":null,"cache_write_5m":1.25,"conditional_meter":null,"ctx":272000,"family":"openai","fast_multiplier":2,"flex_multiplier":0.5,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":1.0,"input":["text"],"label":"OpenAI Chat","max_out":128000,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"gpt-6.1-terra","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.05,"cache_write":1.25,"cache_write_1h":null,"cache_write_5m":1.25,"conditional_meter":null,"ctx":272000,"family":"gemini","fast_multiplier":2,"flex_multiplier":0.5,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":1.0,"input":["text"],"label":"Gemini generateContent","max_out":128000,"max_tool_calls":null,"out":5.0,"output":["text"],"path":"/v1beta/models/{model}:generateContent","request_model_id":"gpt-6.1-terra","route_label":"Core","status_reads":[],"tiers":[],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":922000,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"OpenAI Chat","max_out":128000,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":922000,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"OpenAI Responses","max_out":128000,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1/responses","request_model_id":"gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":922000,"family":"gemini","fast_multiplier":1,"flex_multiplier":1,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"Gemini generateContent","max_out":128000,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1beta/models/gpt-6.1-terra:generateContent","request_model_id":"gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":null,"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":null,"family":"anthropic","fast_multiplier":1,"flex_multiplier":1,"fmt":"messages","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"Anthropic Messages","max_out":null,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1/messages","request_model_id":"openai/gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":{"web_search_call":0.02},"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"responses","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"OpenAI Responses","max_out":null,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1/responses","request_model_id":"openai/gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":{"web_search_call":0.02},"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":null,"family":"openai","fast_multiplier":1,"flex_multiplier":1,"fmt":"chat","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"OpenAI Chat","max_out":null,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1/chat/completions","request_model_id":"openai/gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":{"web_search_call":0.02},"unit":"token","units":[]},{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"conditional_meter":null,"ctx":null,"family":"gemini","fast_multiplier":1,"flex_multiplier":1,"fmt":"gemini","http":"POST","img_in":null,"img_out":null,"in":2.0,"input":["text"],"label":"Gemini generateContent","max_out":null,"max_tool_calls":null,"out":10.0,"output":["text"],"path":"/v1beta/models/openai/gpt-6.1-terra:generateContent","request_model_id":"openai/gpt-6.1-terra","route_label":"Ultra","status_reads":[],"tiers":[{"cache_read":0.1,"cache_write":2.5,"cache_write_1h":2.5,"cache_write_5m":2.5,"in":2.0,"interval_boundary":"min_exclusive_max_inclusive","label":"<=272K","max":272000,"min":0,"null_rate_policy":"inherit_base_rate","out":10.0},{"cache_read":0.2,"cache_write":5.0,"cache_write_1h":5.0,"cache_write_5m":5.0,"in":4.0,"interval_boundary":"min_exclusive_max_inclusive","label":">272K","max":null,"min":272000,"null_rate_policy":"inherit_base_rate","out":15.0}],"tool_prices":{"web_search_call":0.02},"unit":"token","units":[]}],"model_aliases":[{"canonical_model_id":"openai/gpt-6.1-terra","request_model_id":"gpt-6.1-terra","route_label":"Core"},{"canonical_model_id":"openai/gpt-6.1-terra","request_model_id":"gpt-6.1-terra","route_label":"Ultra"},{"canonical_model_id":"openai/gpt-6.1-terra","request_model_id":"openai/gpt-6.1-terra","route_label":"Ultra"}],"name":"OpenAI: GPT-6.1 Terra","price":{"in":1.0,"in_label":null,"out":5.0,"out_label":null,"sort_in":1.0,"sort_out":5.0,"varies":true},"public_id":"openai/gpt-6.1-terra","short":"GPT-6.1 Terra 用於撰寫與編輯清楚文字、分析文件，以及在大型上下文中整理資料。"} ``` ## 常見問題 如何為任務選擇模型？ 先確定需要的輸入與輸出：文字、圖片、音訊或影片，再比較相容的 API 方法、確切的模型 ID 或別名目前指向的模型、價格與計費單位。免費的 GET /v1/models 會列出金鑰可存取的模型。 每個模型都支援所有 API 方法與媒體類型嗎？ 請使用模型卡片列出的 API 方法與輸入、輸出類型。文字、圖片、音訊或影片的支援情況取決於所選模型及方法；傳送資料前請查看對應的請求範例。 模型 ID 與別名有何不同？ 確切的 ID 代表特定模型。別名會指向某個模型，而指向的模型可能變更。請在目錄中查看別名目前指向的模型；整合需要特定模型時，請使用確切的 ID。 傳送請求前如何比較價格？ 在模型卡片中查看所選 API 方法的價格與計費單位。請以相同單位及輸入、輸出類型比較；請求紀錄會顯示實際用量與扣款金額。 訂閱提供什麼？ 持續工作可優惠購買 token。按請求量選方案，訂閱條件與費用在申購時顯示。 如何使用最高 50% 折扣碼？ 購買 token 時輸入折扣碼，總額依活動條件重算，付款前即可看到優惠。 ## Ailoot · 公司及其專案組合 Ailoot以累積的營運經驗、廣大的客戶群、穩定的服務及持續的KPI管理為基礎。 公司及其專案組合：數百萬客戶，每月銷售額達數十億。 Ailoot將這些營運經驗用於API存取，讓客戶的產品、代理、應用程式及自動化流程使用AI功能。