Skip to content

Commit 1a7fc8a

Browse files
sophiasophia
sophia
authored and
sophia
committed
Add Kimi K2.6 pricing docs
1 parent 9c44b9a commit 1a7fc8a

6 files changed

Lines changed: 104 additions & 0 deletions

File tree

‎docs/llmservice/models/kimi-k2.6.md‎

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
# Kimi K2.6
2+
3+
## Overview
4+
5+
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.
6+
7+
## Key Features
8+
9+
* **Multimodal Understanding**: Supports text and visual-context tasks where enabled by the platform configuration.
10+
* **Coding and Technical Workflows**: Suitable for coding assistance, debugging, code review, implementation planning, and UI-oriented generation tasks.
11+
* **Agentic Workflows**: Designed for multi-step tasks that rely on planning, tool use, and iterative execution.
12+
* **Long-Context Analysis**: Can be used for document review, repository understanding, and multi-turn workflows when long-context support is enabled.
13+
* **Cost-Aware Usage**: Provides a lower-cost option for multimodal and agentic tasks compared with many higher-priced flagship models.
14+
15+
## Best Use Cases
16+
17+
* **Coding and UI Generation**: Turning requirements, screenshots, and technical context into implementation plans or code suggestions.
18+
* **Multimodal Document Work**: Understanding documents, diagrams, screenshots, and visual references where supported.
19+
* **Agent and Tool Workflows**: Multi-step workflows that require reasoning, tool calls, and iterative refinement.
20+
* **Cost-Sensitive Production Tasks**: High-frequency workloads where price, latency, and model capability need to be balanced.
21+
22+
## Capabilities and Limitations
23+
24+
| Capability | Description |
25+
| :----------------- | :----------------------------------------------------------------------------------------------- |
26+
| **Reasoning** | Suitable for structured reasoning, technical analysis, and multi-step task planning |
27+
| **Coding** | Supports code generation, debugging, code review, and UI-oriented implementation assistance |
28+
| **Multimodal** | Text and visual input support may be available depending on platform configuration |
29+
| **Response Speed** | Optimized for practical interactive and agent workflows; actual latency may vary by workload |
30+
| **Context Window** | Long-context support is available where enabled by the platform configuration |
31+
| **Max Output** | Output limits may vary by platform configuration and request settings |
32+
| **Tool Use** | Suitable for compatible agent and tool-assisted workflows |
33+
| **Multilingual** | Supports multilingual text tasks, including Chinese and English workflows |
34+
35+
### Known Limitations
36+
37+
* Specific multimodal input formats, context limits, and output limits may vary by B.AI platform configuration.
38+
* External actions, web access, code execution, and tool calls require compatible integrations.
39+
* Model availability and exact runtime behavior may change with the B.AI model catalog and provider-side updates.
40+
* For the latest supported model ID and runtime availability, refer to the platform model selector or API model catalog.
41+
42+
## Credits Usage
43+
44+
| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
45+
| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
46+
| **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - |
47+
48+
:::info Pricing note
49+
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.
50+
:::

‎docs/llmservice/pricing-and-usage.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,7 @@ The platform uses a unified Credits system to measure and settle usage across al
1616
| :---------------- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: |
1717
| MiniMax M3 | 0.30 | 0.30 | 0.06 | 1.20 | - |
1818
| MiniMax M2.7 | 0.30 | 0.375 | 0.06 | 1.20 | - |
19+
| Kimi K2.6 | 0.95 | 0.95 | 0.16 | 4.00 | - |
1920
| Kimi K2.5 | 0.59 | 0.59 | 0.177 | 3.00 | - |
2021
| Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - |
2122
| GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - |

‎i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md‎

Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
# Kimi K2.6
2+
3+
## 概述
4+
5+
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。
6+
7+
## 核心特性
8+
9+
* **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。
10+
* **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。
11+
* **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。
12+
* **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。
13+
* **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。
14+
15+
## 适用场景
16+
17+
* **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。
18+
* **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。
19+
* **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。
20+
* **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。
21+
22+
## 能力与限制
23+
24+
| 能力维度 | 说明 |
25+
| :--- | :--- |
26+
| **推理能力** | 适合结构化推理、技术分析和多步骤任务规划 |
27+
| **编程能力** | 支持代码生成、调试、代码审查和 UI 实现辅助 |
28+
| **多模态能力** | 根据平台配置，可能支持文本和视觉输入 |
29+
| **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 |
30+
| **上下文窗口** | 在平台配置支持时可使用长上下文能力 |
31+
| **最大输出** | 输出上限可能随平台配置和请求设置变化 |
32+
| **工具调用** | 适合兼容的 Agent 和工具辅助工作流 |
33+
| **多语言能力** | 支持包括中文和英文在内的多语言文本任务 |
34+
35+
### 已知限制
36+
37+
* 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。
38+
* 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。
39+
* 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。
40+
* 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。
41+
42+
## 积分消耗
43+
44+
| 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 |
45+
| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
46+
| **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - |
47+
48+
:::info 价格说明
49+
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。
50+
:::

‎i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,7 @@
1616
| :--- | --------------------: | ------------------------: | ------------------------: | --------------------: | ---------------------: |
1717
| MiniMax M3 | 0.30 | 0.30 | 0.06 | 1.20 | - |
1818
| MiniMax M2.7 | 0.30 | 0.375 | 0.06 | 1.20 | - |
19+
| Kimi K2.6 | 0.95 | 0.95 | 0.16 | 4.00 | - |
1920
| Kimi K2.5 | 0.59 | 0.59 | 0.177 | 3.00 | - |
2021
| Qwen3.6-27B | 0.19 | 0.19 | 0.019 | 2.99 | - |
2122
| GLM-5.2 | 1.40 | 1.40 | 0.28 | 4.40 | - |

‎i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -253,6 +253,7 @@ const sidebars = {
253253
'llmservice/models/gemini-3-flash',
254254
'llmservice/models/glm-5-2',
255255
'llmservice/models/glm-5-1',
256+
'llmservice/models/kimi-k2.6',
256257
'llmservice/models/kimi-k2.5',
257258
'llmservice/models/qwen3.6-27b',
258259
'llmservice/models/minimax-m3',

‎sidebars.js‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -250,6 +250,7 @@ const sidebars = {
250250
'llmservice/models/gemini-3-flash',
251251
'llmservice/models/glm-5-2',
252252
'llmservice/models/glm-5-1',
253+
'llmservice/models/kimi-k2.6',
253254
'llmservice/models/kimi-k2.5',
254255
'llmservice/models/qwen3.6-27b',
255256
'llmservice/models/minimax-m3',

0 commit comments

Comments
 (0)