From 091569140368f22cfcf6eaae969be20fbb390dfd Mon Sep 17 00:00:00 2001 From: sophia Date: Mon, 6 Jul 2026 18:35:20 +0800 Subject: [PATCH 1/3] Sync GLM model pricing docs --- docs/llmservice/models/glm-5-1.md | 6 +-- docs/llmservice/models/glm-5-2.md | 4 +- docs/llmservice/models/glm-5.md | 47 ----------------- docs/llmservice/models/minimax-m2.7.md | 2 +- docs/llmservice/pricing-and-usage.md | 1 - .../current/llmservice/models/glm-5-1.md | 6 +-- .../current/llmservice/models/glm-5-2.md | 4 +- .../current/llmservice/models/glm-5.md | 50 ------------------- .../current/llmservice/models/minimax-m2.7.md | 2 +- .../current/llmservice/pricing-and-usage.md | 1 - .../current/sidebars.js | 1 - sidebars.js | 1 - 12 files changed, 12 insertions(+), 113 deletions(-) delete mode 100644 docs/llmservice/models/glm-5.md delete mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md diff --git a/docs/llmservice/models/glm-5-1.md b/docs/llmservice/models/glm-5-1.md index 084bf0b3..31a960a5 100644 --- a/docs/llmservice/models/glm-5-1.md +++ b/docs/llmservice/models/glm-5-1.md @@ -2,7 +2,7 @@ ## Overview -GLM-5.1 is an open-source flagship AI model developed by Z.ai, formerly Zhipu AI, a Tsinghua University spinoff and the first publicly traded foundation model company. Released on April 7, 2026, it is a post-training upgrade to GLM-5, built on a 754-billion-parameter Mixture-of-Experts architecture with 40 billion active parameters per token. GLM-5.1 is designed for agentic engineering and long-horizon autonomous software development. +GLM-5.1 is an open-source flagship AI model developed by Z.ai, formerly Zhipu AI, a Tsinghua University spinoff and the first publicly traded foundation model company. Released on April 7, 2026, it is a post-training upgrade in the GLM family, built on a 754-billion-parameter Mixture-of-Experts architecture with 40 billion active parameters per token. GLM-5.1 is designed for agentic engineering and long-horizon autonomous software development. ## Key Features @@ -23,7 +23,7 @@ GLM-5.1 is an open-source flagship AI model developed by Z.ai, formerly Zhipu AI | :----------------- | :----------------------------------------------------------------------------------------------------------- | | **Reasoning** | AIME 2026: 95.3%, GPQA-Diamond: 86.2%, with strong system-level reasoning across planning and iterative debugging | | **Coding** | SWE-Bench Pro 58.4%, CyberGym 68.7%, BrowseComp 68.0%, MCP-Atlas 71.8% | -| **Multimodal** | Text only. No image, audio, or video input. A separate GLM-5V-Turbo variant is available for vision tasks | +| **Multimodal** | Text only. No image, audio, or video input. Vision tasks require a separate vision-capable model | | **Response Speed** | Not independently benchmarked yet; expected to be comparable to similar-scale MoE models | | **Context Window** | 200K tokens | | **Max Output** | 128K tokens | @@ -32,7 +32,7 @@ GLM-5.1 is an open-source flagship AI model developed by Z.ai, formerly Zhipu AI ### Known Limitations -* Text-only input with no native multimodal support. Vision use cases rely on the separate GLM-5V-Turbo model. +* Text-only input with no native multimodal support. Vision use cases rely on a separate vision-capable model. * Math and science benchmark scores trail some top proprietary models, making it less suitable for purely quantitative research tasks. * On broader coding composites such as Terminal-Bench 2.0 plus NL2Repo, Claude Opus 4.6 still leads. * Self-hosting requires substantial compute resources because of the 754B parameter count. diff --git a/docs/llmservice/models/glm-5-2.md b/docs/llmservice/models/glm-5-2.md index 4fdc18f5..ca42f46c 100644 --- a/docs/llmservice/models/glm-5-2.md +++ b/docs/llmservice/models/glm-5-2.md @@ -24,7 +24,7 @@ GLM-5.2 is a GLM-family text foundation model developed by Z.AI and released on | **Reasoning** | Supports deep-thinking mode and `reasoning_effort`; Z.AI positions it for complex engineering, debugging, and long-chain reasoning workflows. | | **Creative Writing** | Supports general text generation through the chat completion API, but official GLM-5.2 materials emphasize coding and engineering use cases. | | **Coding** | Z.AI reports Terminal-Bench 2.1 score of 81.0 and SWE-bench Pro score of 62.1, with focus on long-horizon coding-agent scenarios. | -| **Multimodal** | Text input and text output. Vision and multimodal workflows are handled by separate Z.AI models such as GLM-5V-Turbo. | +| **Multimodal** | Text input and text output. Vision and multimodal workflows are handled by separate Z.AI vision-language models. | | **Response Speed** | Official docs do not publish latency or tokens-per-second figures; streaming responses and streaming tool calls are supported. | | **Context Window** | 1M tokens. | | **Max Output** | 128K tokens. | @@ -33,7 +33,7 @@ GLM-5.2 is a GLM-family text foundation model developed by Z.AI and released on ### Known Limitations -* Text-only model; image, video, and GUI-understanding tasks require a separate vision-language model such as GLM-5V-Turbo. +* Text-only model; image, video, and GUI-understanding tasks require a separate vision-language model. * Very long contexts and 128K outputs can increase latency and cost; cap `max_tokens` and use context caching where applicable. ## Credits Usage diff --git a/docs/llmservice/models/glm-5.md b/docs/llmservice/models/glm-5.md deleted file mode 100644 index 0d43c678..00000000 --- a/docs/llmservice/models/glm-5.md +++ /dev/null @@ -1,47 +0,0 @@ -# GLM-5 - -## Overview -**GLM-5** is Zhipu AI's new-generation flagship foundation model, specifically designed for **Coding** and **Agent** scenarios. It achieves State-Of-The-Art (SOTA) performance in open-source complex system engineering and long-horizon tasks, with a real-world coding experience approaching **Claude Opus** level. - -Based on a **744B** scale foundation model, combined with asynchronous reinforcement learning and sparse attention mechanisms, GLM-5 marks a paradigm shift from "writing code" to "building systems". - ---- - -## Key Features -* **Parameter Scale and Data Volume:** The base model's parameter scale has expanded to **744B** (with **40B** activated parameters), and pre-training data has increased to **28.5T**, significantly enhancing the model's breadth and depth of knowledge. -* **Ultra-Long Context and Output:** Supports a context window of up to **200K tokens** and a maximum output length of **128K tokens**, enabling excellent performance in handling complex code repositories and multi-step tasks. -* **Exceptional Coding & Agent Capabilities:** Systematically strengthened programming capabilities, excelling in code generation with low hallucination rates and efficient token utilization. -* **Multiple Thinking Modes:** Offers various thinking modes to support more flexible and in-depth problem-solving. - ---- - -## Best Use Cases -1. **Complex System Engineering:** Construction and management of complex software systems, assisting in system design and optimization. -2. **Long-Horizon Agent Tasks:** Agent tasks requiring multi-step planning, execution, and feedback (e.g., automated workflows). -3. **High-Precision Code Debugging:** Provides human-level coding assistance to improve development efficiency. -4. **Large-Scale Document Analysis:** Deep information extraction and summarization for massive document sets. - ---- - -## Capabilities and Limitations - -| Capability | Detailed Description | -| :--- | :--- | -| **Reasoning Ability** | **Extremely Strong.** Excels in complex logical reasoning and multi-step planning. | -| **Creative Ability** | **Extremely Strong.** Particularly adept at code generation and system design. | -| **Multimodal Ability** | Primarily focuses on text/code; can be integrated with visual tools on Zhipu platform. | -| **Response Speed** | **30-50 tokens/s.** Balances high-quality output with efficient speed. | -| **Context Window** | 200K Tokens | -| **Max Output** | 128K Tokens | - ---- - -## Credits Usage - -| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | -| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | -| **GLM-5** | `1.00` | `1.00` | `0.20` | `3.20` | `-` | - | - -:::info Pricing note -Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records. -::: diff --git a/docs/llmservice/models/minimax-m2.7.md b/docs/llmservice/models/minimax-m2.7.md index e1602ec3..f0b1ba1c 100644 --- a/docs/llmservice/models/minimax-m2.7.md +++ b/docs/llmservice/models/minimax-m2.7.md @@ -6,7 +6,7 @@ MiniMax M2.7 is a reasoning-focused large language model developed by MiniMax (S ## Key Features -* **Cost-Efficient Reasoning**: Achieves intelligence scores comparable to GLM-5 and Kimi K2.5 while costing roughly one-third as much to run, with 20% fewer output tokens needed for equivalent results. +* **Cost-Efficient Reasoning**: Delivers strong reasoning performance at a lower operating cost than many flagship models, with 20% fewer output tokens needed for equivalent results. * **Low Hallucination Rate**: Scores a 34% hallucination rate on the AA-Omniscience Index, lower than Claude Sonnet 4.6 and Gemini 3.1 Pro Preview. * **Multi-Agent Collaboration**: Native support for multi-agent orchestration and complex skill coordination, including dynamic tool discovery and invocation at runtime. * **Self-Evolution**: Can autonomously complete 30-50% of reinforcement-learning research workflows, representing an early step toward model self-improvement. diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index 484059b8..42ed3bad 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -20,7 +20,6 @@ The platform uses a unified Credits system to measure and settle usage across al | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | | GLM-5.1 | 1.40 | 1.40 | 0.26 | 4.40 | - | -| GLM-5 | 1.00 | 1.00 | 0.20 | 3.20 | - | | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | | DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md index b1edd1bf..d2b237a6 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md @@ -2,7 +2,7 @@ ## 概述 -GLM-5.1 是由 Z.ai 开发的开源旗舰 AI 模型。Z.ai 前身为智谱 AI，源自清华大学，也是首家公开上市的基础模型公司。GLM-5.1 于 2026 年 4 月 7 日发布，是在 GLM-5 基础上的一次后训练升级，采用 7540 亿参数的 Mixture-of-Experts 架构，每个 token 激活约 400 亿参数，重点面向 Agent 工程与长周期自主软件开发场景。 +GLM-5.1 是由 Z.ai 开发的开源旗舰 AI 模型。Z.ai 前身为智谱 AI，源自清华大学，也是首家公开上市的基础模型公司。GLM-5.1 于 2026 年 4 月 7 日发布，是 GLM 系列的一次后训练升级，采用 7540 亿参数的 Mixture-of-Experts 架构，每个 token 激活约 400 亿参数，重点面向 Agent 工程与长周期自主软件开发场景。 ## 核心特性 @@ -23,7 +23,7 @@ GLM-5.1 是由 Z.ai 开发的开源旗舰 AI 模型。Z.ai 前身为智谱 AI， | :--- | :--- | | **推理能力** | AIME 2026：95.3%，GPQA-Diamond：86.2%，在规划与迭代调试场景中具备较强的系统级推理能力 | | **编程能力** | SWE-Bench Pro 58.4%，CyberGym 68.7%，BrowseComp 68.0%，MCP-Atlas 71.8% | -| **多模态能力** | 仅支持文本，不支持图像、音频或视频输入；视觉场景可使用单独的 GLM-5V-Turbo 变体 | +| **多模态能力** | 仅支持文本，不支持图像、音频或视频输入；视觉场景需要使用单独的视觉能力模型 | | **响应速度** | 暂无独立公开测速结果，预计与同规模 MoE 模型相近 | | **上下文窗口** | 200K tokens | | **最大输出** | 128K tokens | @@ -32,7 +32,7 @@ GLM-5.1 是由 Z.ai 开发的开源旗舰 AI 模型。Z.ai 前身为智谱 AI， ### 已知限制 -* 仅支持文本输入，不具备原生多模态能力；视觉任务需依赖独立的 GLM-5V-Turbo 模型。 +* 仅支持文本输入，不具备原生多模态能力；视觉任务需依赖独立的视觉能力模型。 * 数学与科学基准成绩仍落后于部分顶级专有模型，因此在纯量化研究任务上不一定是最优选择。 * 在更广泛的编码综合评测（如 Terminal-Bench 2.0 + NL2Repo）中，Claude Opus 4.6 仍然领先。 * 由于参数规模达到 754B，自托管需要较高的计算资源。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md index 1683b6e2..fa1351f8 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-2.md @@ -24,7 +24,7 @@ GLM-5.2 是由 Z.AI 开发的 GLM 系列文本基础模型，于 2026 年 6 月 | **推理能力** | 支持 deep-thinking 模式和 `reasoning_effort`；Z.AI 将其定位于复杂工程、调试和长链路推理工作流 | | **创意写作** | 支持通过 chat completion API 进行通用文本生成，但官方 GLM-5.2 材料更强调代码和工程场景 | | **编程能力** | Z.AI 报告 Terminal-Bench 2.1 得分为 81.0，SWE-bench Pro 得分为 62.1，重点面向长周期 Coding Agent 场景 | -| **多模态能力** | 文本输入和文本输出；视觉和多模态工作流由 GLM-5V-Turbo 等独立 Z.AI 模型处理 | +| **多模态能力** | 文本输入和文本输出；视觉和多模态工作流由独立的 Z.AI 视觉语言模型处理 | | **响应速度** | 官方文档未公布延迟或 tokens-per-second 数据；支持流式响应和流式工具调用 | | **上下文窗口** | 1M tokens | | **最大输出** | 128K tokens | @@ -33,7 +33,7 @@ GLM-5.2 是由 Z.AI 开发的 GLM 系列文本基础模型，于 2026 年 6 月 ### 已知限制 -* 该模型为文本模型；图像、视频和 GUI 理解任务需要使用 GLM-5V-Turbo 等独立视觉语言模型。 +* 该模型为文本模型；图像、视频和 GUI 理解任务需要使用独立视觉语言模型。 * 超长上下文和 128K 输出可能增加延迟和成本；建议按需限制 `max_tokens`，并在适用场景使用上下文缓存。 ## 积分消耗 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md deleted file mode 100644 index 4a5f51f8..00000000 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md +++ /dev/null @@ -1,50 +0,0 @@ -# GLM-5 - -## 概述 - -**GLM-5** 是智谱 AI 推出的新一代旗舰基础模型，专为 **编程（Coding）** 与 **Agent** 场景设计。在开源复杂系统工程与长周期任务中达到 SOTA 表现，实际编码能力接近 **Claude Opus** 水平。 - -基于 **744B** 规模模型，结合异步强化学习与稀疏注意力机制，实现从“写代码”到“构建系统”的能力跃迁。 - ---- - -## 核心特性 - -- **大规模参数与数据：** 模型规模达 **744B（激活 40B）**，预训练数据 **28.5T**，显著提升知识广度与深度 -- **超长上下文与输出：** 支持 **200K Token 上下文**，最大输出 **128K Token**，适合复杂代码与多步骤任务 -- **强大编程与 Agent 能力：** 编程能力系统性增强，低幻觉率，高 Token 利用效率 -- **多种思维模式：** 支持不同推理模式，提升问题解决的灵活性与深度 - ---- - -## 适用场景 - -1. **复杂系统工程：** 软件系统构建、架构设计与优化 -2. **长周期 Agent 任务：** 多步骤规划与执行的自动化流程 -3. **高精度代码调试：** 提供接近人类水平的编程辅助 -4. **大规模文档分析：** 海量文档的信息提取与总结 - ---- - -## 能力与限制 - -| 能力 | 说明 | -| :--- | :--- | -| **推理能力** | 极强。擅长复杂逻辑推理与多步骤规划 | -| **创造能力** | 极强。尤其在代码生成与系统设计方面表现突出 | -| **多模态能力** | 以文本与代码为主，可结合智谱平台视觉能力 | -| **响应速度** | 30–50 tokens/s，在质量与速度之间取得平衡 | -| **上下文窗口** | 200K Token | -| **最大输出** | 128K Token | - ---- - -## 积分消耗 - -| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 | -| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | -| **GLM-5** | `1.00` | `1.00` | `0.20` | `3.20` | `-` | - | - -:::info 价格说明 -文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。 -::: diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md index ec35be91..e35beb1b 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md @@ -6,7 +6,7 @@ MiniMax M2.7 是由 MiniMax（上海）开发的推理型大语言模型，于 2 ## 核心特性 -* **高性价比推理能力**：在智能表现上可与 GLM-5 和 Kimi K2.5 对标，但运行成本约为其三分之一，同时在等效任务下所需输出 token 减少约 20%。 +* **高性价比推理能力**：在较低运行成本下提供较强推理表现，同时在等效任务下所需输出 token 减少约 20%。 * **较低幻觉率**：在 AA-Omniscience Index 上的幻觉率为 34%，低于 Claude Sonnet 4.6 和 Gemini 3.1 Pro Preview。 * **多 Agent 协作**：原生支持多 Agent 编排和复杂技能协同，包括运行时动态工具发现与调用。 * **自进化能力**：可自主完成约 30%-50% 的强化学习研究工作流，体现出早期的模型自我改进能力。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md index f487ebaf..7c086965 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md @@ -20,7 +20,6 @@ | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | | GLM-5.1 | 1.40 | 1.40 | 0.26 | 4.40 | - | -| GLM-5 | 1.00 | 1.00 | 0.20 | 3.20 | - | | DeepSeek V3.2 | 0.29 | 0.29 | 0.145 | 0.44 | - | | DeepSeek V4 Flash | 0.28 | 0.28 | 0.0056 | 0.56 | - | | DeepSeek V4 Pro | 0.87 | 0.87 | 0.0087 | 1.74 | - | diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js index f000ff6a..6c629822 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js @@ -253,7 +253,6 @@ const sidebars = { 'llmservice/models/gemini-3-flash', 'llmservice/models/glm-5-2', 'llmservice/models/glm-5-1', - 'llmservice/models/glm-5', 'llmservice/models/kimi-k2.5', 'llmservice/models/qwen3.6-27b', 'llmservice/models/minimax-m3', diff --git a/sidebars.js b/sidebars.js index c8a4d9de..d009f2a0 100644 --- a/sidebars.js +++ b/sidebars.js @@ -250,7 +250,6 @@ const sidebars = { 'llmservice/models/gemini-3-flash', 'llmservice/models/glm-5-2', 'llmservice/models/glm-5-1', - 'llmservice/models/glm-5', 'llmservice/models/kimi-k2.5', 'llmservice/models/qwen3.6-27b', 'llmservice/models/minimax-m3', From 9c44b9a96f5bd05b00ad60bb9f01bc0f2dc421b3 Mon Sep 17 00:00:00 2001 From: jerryji-prog Date: Tue, 7 Jul 2026 10:43:36 +0800 Subject: [PATCH 2/3] add version --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index 64f56fc1..0931c5fe 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@x402-tron/docs", - "version": "1.3.2", + "version": "1.3.3", "description": "x402-tron documentation", "license": "MIT", "scripts": { From 1a7fc8a01d08005ee45beb8c9ceaf2ff983c2a44 Mon Sep 17 00:00:00 2001 From: sophia Date: Tue, 7 Jul 2026 13:38:42 +0800 Subject: [PATCH 3/3] Add Kimi K2.6 pricing docs --- docs/llmservice/models/kimi-k2.6.md | 50 +++++++++++++++++++ docs/llmservice/pricing-and-usage.md | 1 + .../current/llmservice/models/kimi-k2.6.md | 50 +++++++++++++++++++ .../current/llmservice/pricing-and-usage.md | 1 + .../current/sidebars.js | 1 + sidebars.js | 1 + 6 files changed, 104 insertions(+) create mode 100644 docs/llmservice/models/kimi-k2.6.md create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md diff --git a/docs/llmservice/models/kimi-k2.6.md b/docs/llmservice/models/kimi-k2.6.md new file mode 100644 index 00000000..b4a59e20 --- /dev/null +++ b/docs/llmservice/models/kimi-k2.6.md @@ -0,0 +1,50 @@ +# Kimi K2.6 + +## Overview + +Kimi K2.6 is a Moonshot AI model available on B.AI for multimodal understanding, coding assistance, long-context analysis, and agentic workflows. It is suitable for tasks that combine text, visual context, structured reasoning, and tool-assisted execution. Specific capabilities, input formats, context limits, and availability may vary by B.AI model catalog and platform configuration. + +## Key Features + +* **Multimodal Understanding**: Supports text and visual-context tasks where enabled by the platform configuration. +* **Coding and Technical Workflows**: Suitable for coding assistance, debugging, code review, implementation planning, and UI-oriented generation tasks. +* **Agentic Workflows**: Designed for multi-step tasks that rely on planning, tool use, and iterative execution. +* **Long-Context Analysis**: Can be used for document review, repository understanding, and multi-turn workflows when long-context support is enabled. +* **Cost-Aware Usage**: Provides a lower-cost option for multimodal and agentic tasks compared with many higher-priced flagship models. + +## Best Use Cases + +* **Coding and UI Generation**: Turning requirements, screenshots, and technical context into implementation plans or code suggestions. +* **Multimodal Document Work**: Understanding documents, diagrams, screenshots, and visual references where supported. +* **Agent and Tool Workflows**: Multi-step workflows that require reasoning, tool calls, and iterative refinement. +* **Cost-Sensitive Production Tasks**: High-frequency workloads where price, latency, and model capability need to be balanced. + +## Capabilities and Limitations + +| Capability | Description | +| :----------------- | :----------------------------------------------------------------------------------------------- | +| **Reasoning** | Suitable for structured reasoning, technical analysis, and multi-step task planning | +| **Coding** | Supports code generation, debugging, code review, and UI-oriented implementation assistance | +| **Multimodal** | Text and visual input support may be available depending on platform configuration | +| **Response Speed** | Optimized for practical interactive and agent workflows; actual latency may vary by workload | +| **Context Window** | Long-context support is available where enabled by the platform configuration | +| **Max Output** | Output limits may vary by platform configuration and request settings | +| **Tool Use** | Suitable for compatible agent and tool-assisted workflows | +| **Multilingual** | Supports multilingual text tasks, including Chinese and English workflows | + +### Known Limitations + +* Specific multimodal input formats, context limits, and output limits may vary by B.AI platform configuration. +* External actions, web access, code execution, and tool calls require compatible integrations. +* Model availability and exact runtime behavior may change with the B.AI model catalog and provider-side updates. +* For the latest supported model ID and runtime availability, refer to the platform model selector or API model catalog. + +## Credits Usage + +| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes | +| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- | +| **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - | + +:::info Pricing note +Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records. +::: diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index 42ed3bad..a0bd6f19 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -16,6 +16,7 @@ The platform uses a unified Credits system to measure and settle usage across al | :---------------- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | | MiniMax M3 | 0.30 | 0.30 | 0.06 | 1.20 | - | | MiniMax M2.7 | 0.30 | 0.375 | 0.06 | 1.20 | - | +| Kimi K2.6 | 0.95 | 0.95 | 0.16 | 4.00 | - | | Kimi K2.5 | 0.59 | 0.59 | 0.177 | 3.00 | - | | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md new file mode 100644 index 00000000..037d2bac --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md @@ -0,0 +1,50 @@ +# Kimi K2.6 + +## 概述 + +Kimi K2.6 是 B.AI 上可用的 Moonshot AI 模型，面向多模态理解、代码辅助、长上下文分析和 Agent 工作流。它适合需要结合文本、视觉上下文、结构化推理和工具辅助执行的任务。具体能力、输入格式、上下文长度和可用状态可能会随 B.AI 模型目录和平台配置调整。 + +## 核心特性 + +* **多模态理解**：在平台配置支持时，可用于文本和视觉上下文相关任务。 +* **代码与技术工作流**：适合代码辅助、调试、代码审查、实现规划和 UI 生成相关任务。 +* **Agent 工作流**：面向依赖规划、工具调用和迭代执行的多步骤任务。 +* **长上下文分析**：在启用长上下文能力时，可用于文档审阅、代码库理解和多轮工作流。 +* **成本友好**：相比许多更高价格的旗舰模型，可作为多模态和 Agent 任务中的低成本选择。 + +## 适用场景 + +* **代码与 UI 生成**：将需求、截图和技术上下文转化为实现方案或代码建议。 +* **多模态文档处理**：在支持的场景下理解文档、图表、截图和视觉参考。 +* **Agent 与工具工作流**：需要推理、工具调用和迭代优化的多步骤工作流。 +* **成本敏感型生产任务**：适合需要在价格、延迟和模型能力之间取得平衡的高频任务。 + +## 能力与限制 + +| 能力维度 | 说明 | +| :--- | :--- | +| **推理能力** | 适合结构化推理、技术分析和多步骤任务规划 | +| **编程能力** | 支持代码生成、调试、代码审查和 UI 实现辅助 | +| **多模态能力** | 根据平台配置，可能支持文本和视觉输入 | +| **响应速度** | 面向实际交互和 Agent 工作流优化，实际延迟会随任务负载变化 | +| **上下文窗口** | 在平台配置支持时可使用长上下文能力 | +| **最大输出** | 输出上限可能随平台配置和请求设置变化 | +| **工具调用** | 适合兼容的 Agent 和工具辅助工作流 | +| **多语言能力** | 支持包括中文和英文在内的多语言文本任务 | + +### 已知限制 + +* 具体多模态输入格式、上下文长度和输出上限可能会随 B.AI 平台配置变化。 +* 外部动作、联网访问、代码执行和工具调用需要兼容的集成环境。 +* 模型可用状态和实际运行行为可能会随 B.AI 模型目录及模型提供方更新而变化。 +* 最新支持的模型 ID 和运行时可用状态，请以平台模型选择器或 API 模型目录为准。 + +## 积分消耗 + +| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 | +| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- | +| **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - | + +:::info 价格说明 +文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。 +::: diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md index 7c086965..ee4add23 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md @@ -16,6 +16,7 @@ | :--- | --------------------: | ------------------------: | ------------------------: | --------------------: | ---------------------: | | MiniMax M3 | 0.30 | 0.30 | 0.06 | 1.20 | - | | MiniMax M2.7 | 0.30 | 0.375 | 0.06 | 1.20 | - | +| Kimi K2.6 | 0.95 | 0.95 | 0.16 | 4.00 | - | | Kimi K2.5 | 0.59 | 0.59 | 0.177 | 3.00 | - | | Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - | | GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - | diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js index 6c629822..0319bf4d 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js @@ -253,6 +253,7 @@ const sidebars = { 'llmservice/models/gemini-3-flash', 'llmservice/models/glm-5-2', 'llmservice/models/glm-5-1', + 'llmservice/models/kimi-k2.6', 'llmservice/models/kimi-k2.5', 'llmservice/models/qwen3.6-27b', 'llmservice/models/minimax-m3', diff --git a/sidebars.js b/sidebars.js index d009f2a0..205fcbf0 100644 --- a/sidebars.js +++ b/sidebars.js @@ -250,6 +250,7 @@ const sidebars = { 'llmservice/models/gemini-3-flash', 'llmservice/models/glm-5-2', 'llmservice/models/glm-5-1', + 'llmservice/models/kimi-k2.6', 'llmservice/models/kimi-k2.5', 'llmservice/models/qwen3.6-27b', 'llmservice/models/minimax-m3',