{ "aboutHtml": "

Reflection 的 Beam 1.0

Beam 1.0 501B A23B 是 Reflection 用於程式設計、推理及多個相關步驟任務的文字模型。其稀疏 MoE 架構總計含 5013 億參數，每個 token 啟用約 234 億參數。模型主要針對英語開發，選擇原始碼、技術資料及詳細指示的語言時，可將此點納入考量。

架構結合局部與全域注意力，模型訓練包含原始碼、技術文件、科學及教學資料。另有訓練階段透過結構化儲存庫、長任務及大型文件培養長上下文能力。強化學習時，開發商結合了程式設計、終端機操作及 STEM 任務。

模型著重哪些工作

Reflection 強調軟體工程、數學與科學推理，以及連續解題。這些方向可用於有內容的文字對話：解釋程式元件間的關係、分析邏輯錯誤、提出演算法修改、規劃假設驗證，或整理技術資料摘要。

Beam 也特別著重節省推理 token。訓練會獎勵在減少多餘 token 的情況下成功解題。這描述的是開發商的方法；具體請求仍宜明確指定答案長度，例如簡短結論、詳細證明，或附說明的修補內容。

Ailoot 的大型文字上下文

此連線的上下文視窗為 1,048,576 個 token，包含提供資料、指示、歷史與生成中的答案。模型中繼資料標示的答案容量最多為 131,072 個 token。這個容量可傳入數份相關文字：規格、實作片段、驗證結果與相關問題。請為資料命名，並要求標示每項結論依據哪個片段，方便核對大型分析。

例如，程式碼工作可先要求依傳入檔案建立相依關係圖，再指出修改位置，最後準備實作。科學問題則可提供初始條件、符號定義及所需嚴謹程度。這些請求安排能讓實用結果與原始資料逐一比對。

此連線透過 Messages、Responses、Chat Completions 及文字 generateContent 接受文字並傳回文字。程式碼與建議以模型答案形式提供；命令執行及外部資料處理由應用程式能力決定。

", "aboutText": "### Reflection 的 Beam 1.0\n\nBeam 1.0 501B A23B 是 Reflection 用於程式設計、推理及多個相關步驟任務的文字模型。其稀疏 MoE 架構總計含 5013 億參數，每個 token 啟用約 234 億參數。模型主要針對英語開發，選擇原始碼、技術資料及詳細指示的語言時，可將此點納入考量。\n\n架構結合局部與全域注意力，模型訓練包含原始碼、技術文件、科學及教學資料。另有訓練階段透過結構化儲存庫、長任務及大型文件培養長上下文能力。強化學習時，開發商結合了程式設計、終端機操作及 STEM 任務。\n\n### 模型著重哪些工作\n\nReflection 強調軟體工程、數學與科學推理，以及連續解題。這些方向可用於有內容的文字對話：解釋程式元件間的關係、分析邏輯錯誤、提出演算法修改、規劃假設驗證，或整理技術資料摘要。\n\nBeam 也特別著重節省推理 token。訓練會獎勵在減少多餘 token 的情況下成功解題。這描述的是開發商的方法；具體請求仍宜明確指定答案長度，例如簡短結論、詳細證明，或附說明的修補內容。\n\n### Ailoot 的大型文字上下文\n\n此連線的上下文視窗為 1,048,576 個 token，包含提供資料、指示、歷史與生成中的答案。模型中繼資料標示的答案容量最多為 131,072 個 token。這個容量可傳入數份相關文字：規格、實作片段、驗證結果與相關問題。請為資料命名，並要求標示每項結論依據哪個片段，方便核對大型分析。\n\n例如，程式碼工作可先要求依傳入檔案建立相依關係圖，再指出修改位置，最後準備實作。科學問題則可提供初始條件、符號定義及所需嚴謹程度。這些請求安排能讓實用結果與原始資料逐一比對。\n\n此連線透過 Messages、Responses、Chat Completions 及文字 generateContent 接受文字並傳回文字。程式碼與建議以模型答案形式提供；命令執行及外部資料處理由應用程式能力決定。", "locale": "zh-hant-tw", "methods": [ { "html": "
Ultra Anthropic MessagesPOST /v1/messages
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$0.0005 / 1K
輸出
US$0.002 / 1K
讀取快取
US$0.0001 / 1K
", "method_identity": { "effective_request_model_id": "reflection/beam-1.0-501b-a23b", "fmt": "messages", "http": "POST", "path": "/v1/messages", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra" }, "method_key": "Ultra|messages|/v1/messages|reflection%2Fbeam-1.0-501b-a23b", "ordinal": 0, "rawMethod": { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "Anthropic Messages", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/messages", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } }, { "html": "
Ultra OpenAI ResponsesPOST /v1/responses
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$0.0005 / 1K
輸出
US$0.002 / 1K
讀取快取
US$0.0001 / 1K
", "method_identity": { "effective_request_model_id": "reflection/beam-1.0-501b-a23b", "fmt": "responses", "http": "POST", "path": "/v1/responses", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra" }, "method_key": "Ultra|responses|/v1/responses|reflection%2Fbeam-1.0-501b-a23b", "ordinal": 1, "rawMethod": { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "OpenAI Responses", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/responses", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } }, { "html": "
Ultra OpenAI ChatPOST /v1/chat/completions
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$0.0005 / 1K
輸出
US$0.002 / 1K
讀取快取
US$0.0001 / 1K
", "method_identity": { "effective_request_model_id": "reflection/beam-1.0-501b-a23b", "fmt": "chat", "http": "POST", "path": "/v1/chat/completions", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra" }, "method_key": "Ultra|chat|/v1/chat/completions|reflection%2Fbeam-1.0-501b-a23b", "ordinal": 2, "rawMethod": { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/chat/completions", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } }, { "html": "
Ultra Gemini generateContentPOST /v1beta/models/reflection/beam-1.0-501b-a23b:generateContent
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$0.0005 / 1K
輸出
US$0.002 / 1K
讀取快取
US$0.0001 / 1K
", "method_identity": { "effective_request_model_id": "reflection/beam-1.0-501b-a23b", "fmt": "gemini", "http": "POST", "path": "/v1beta/models/reflection/beam-1.0-501b-a23b:generateContent", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra" }, "method_key": "Ultra|gemini|/v1beta/models/reflection/beam-1.0-501b-a23b:generateContent|reflection%2Fbeam-1.0-501b-a23b", "ordinal": 3, "rawMethod": { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "Gemini generateContent", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1beta/models/reflection/beam-1.0-501b-a23b:generateContent", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } } ], "model_id": "reflection/beam-1.0-501b-a23b", "page": { "canonical": "https://ailoot.ai/models/zh-hant-tw/reflection-beam-1-0-501b-a23b/", "description": "Reflection 的大型上下文文字 MoE 模型，用於軟體工程、數學推理與逐步分析問題。", "locale": "zh-hant-tw", "md_url": "https://ailoot.ai/models/zh-hant-tw/reflection-beam-1-0-501b-a23b/index.md", "title": "Reflection: Beam 1.0 501B A23B", "url": "https://ailoot.ai/models/zh-hant-tw/reflection-beam-1-0-501b-a23b/" }, "rawModel": { "about": "### Reflection 的 Beam 1.0\n\nBeam 1.0 501B A23B 是 Reflection 用於程式設計、推理及多個相關步驟任務的文字模型。其稀疏 MoE 架構總計含 5013 億參數，每個 token 啟用約 234 億參數。模型主要針對英語開發，選擇原始碼、技術資料及詳細指示的語言時，可將此點納入考量。\n\n架構結合局部與全域注意力，模型訓練包含原始碼、技術文件、科學及教學資料。另有訓練階段透過結構化儲存庫、長任務及大型文件培養長上下文能力。強化學習時，開發商結合了程式設計、終端機操作及 STEM 任務。\n\n### 模型著重哪些工作\n\nReflection 強調軟體工程、數學與科學推理，以及連續解題。這些方向可用於有內容的文字對話：解釋程式元件間的關係、分析邏輯錯誤、提出演算法修改、規劃假設驗證，或整理技術資料摘要。\n\nBeam 也特別著重節省推理 token。訓練會獎勵在減少多餘 token 的情況下成功解題。這描述的是開發商的方法；具體請求仍宜明確指定答案長度，例如簡短結論、詳細證明，或附說明的修補內容。\n\n### Ailoot 的大型文字上下文\n\n此連線的上下文視窗為 1,048,576 個 token，包含提供資料、指示、歷史與生成中的答案。模型中繼資料標示的答案容量最多為 131,072 個 token。這個容量可傳入數份相關文字：規格、實作片段、驗證結果與相關問題。請為資料命名，並要求標示每項結論依據哪個片段，方便核對大型分析。\n\n例如，程式碼工作可先要求依傳入檔案建立相依關係圖，再指出修改位置，最後準備實作。科學問題則可提供初始條件、符號定義及所需嚴謹程度。這些請求安排能讓實用結果與原始資料逐一比對。\n\n此連線透過 Messages、Responses、Chat Completions 及文字 generateContent 接受文字並傳回文字。程式碼與建議以模型答案形式提供；命令執行及外部資料處理由應用程式能力決定。", "alias_of": null, "aliases": [], "author": "Reflection", "canonical_model": "reflection/beam-1.0-501b-a23b", "ctx": null, "formats": [ "chat", "gemini", "messages", "responses" ], "id": "reflection/beam-1.0-501b-a23b", "input": [ "text" ], "kind": "text", "max_out": null, "methods": [ { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "Anthropic Messages", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/messages", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] }, { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "OpenAI Responses", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/responses", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] }, { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "OpenAI Chat", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1/chat/completions", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] }, { "cache_read": 0.1, "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": 0.5, "input": [ "text" ], "label": "Gemini generateContent", "max_out": null, "max_tool_calls": null, "out": 2.0, "output": [ "text" ], "path": "/v1beta/models/reflection/beam-1.0-501b-a23b:generateContent", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "token", "units": [] } ], "model_aliases": [ { "canonical_model_id": "reflection/beam-1.0-501b-a23b", "request_model_id": "reflection/beam-1.0-501b-a23b", "route_label": "Ultra" } ], "name": "Reflection: Beam 1.0 501B A23B", "price": { "in": 0.5, "in_label": null, "out": 2.0, "out_label": null, "sort_in": 0.5, "sort_out": 2.0, "varies": false }, "public_id": "reflection/beam-1.0-501b-a23b", "short": "Reflection 的大型上下文文字 MoE 模型，用於軟體工程、數學推理與逐步分析問題。" }, "renderer_schema": { "method_order": "rawModel.methods-ordinal", "prices": "exact-native-DTO-units-and-selected-renderer-html" }, "representation": "exact-public-dto-and-native-renderer-html", "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Reflection 的大型上下文文字 MoE 模型，用於軟體工程、數學推理與逐步分析問題。", "source": { "audit_sha256": "c55b1b40bec2a827ffe18bee6d521abd7312cfd32db6837e050ea501cd53112b", "bridge_map_sha256": "c55b1b40bec2a827ffe18bee6d521abd7312cfd32db6837e050ea501cd53112b", "projection_audit": { "parent_manifest_sha256": "dfd3a7a4bc6f960e128026cae1f98f769d1503ffa1c6cf0ccf80066382dbbb9e", "raw_model_json_sha256": "bbd41253f14fc2da31e775b0d92a2d003e4b5a3f107530eb116a0d2b9d58a534", "renderer_sha256": "ff9782d9ac535c4c4d8dcf64caf6d1647fda3a5c20c28fe9033f27d2c7d287f5" }, "projection_kind": "catalogue-refresh-native-dto-v1", "raw_model_json_sha256": "bbd41253f14fc2da31e775b0d92a2d003e4b5a3f107530eb116a0d2b9d58a534", "renderer_sha256": "ff9782d9ac535c4c4d8dcf64caf6d1647fda3a5c20c28fe9033f27d2c7d287f5" }, "sourceRevision": "15ab7bfe0645eb0d01d61c6575b4cf8ea8e304db71d4b7e13feda8d79c1722be" }