Overview
Kimi API 开放平台
Kimi K3.1 Pro 是 Kimi 面向长程编程与端到端知识工作的旗舰模型,1M token 上下文,综合智能达到领先水平。Kimi API 开放平台提供多款大模型 API,支持超长上下文、多模态理解与 Tool Calling。
Content and agent signals
For agents (AI-generated): Kimi API open platform: documentation and API access to Kimi LLMs (K3.1 Pro, K3, K2.7 Code, K2.6) with 1M context, tool calling, streaming and multimodal input.
kimi apilarge language modeltool callinglong contextmultimodal
Files
Publisher files and the directory’s indexed copy.
Read the cached llms.txt preview
Their llms.txt
The beginning of the file, from our validated copy saved 2026-11-14T23:32:24.363Z. Cached copy · Source on kimi.com
# Kimi API 开放平台
> Kimi K3.1 Pro 是 Kimi 面向长程编程与端到端知识工作的旗舰模型,1M token 上下文,综合智能达到领先水平。Kimi API 开放平台提供多款大模型 API,支持超长上下文、多模态理解与 Tool Calling。
- [快速开始](https://platform.kimi.com/docs/get-api-key.md): 从创建 API Key 到完成第一次 Kimi API 调用。
- [功能总览](https://platform.kimi.com/docs/features.md): 按模型推理、工具调用、生态集成和托管智能体查看 Kimi 开放平台的主要能力,并跳转到对应使用文档。
- [Kimi K3.1 Pro](https://platform.kimi.com/docs/guide/kimi-k3-1-pro-quickstart.md): 了解 Kimi K3.1 Pro 的 API 调用方式:推理强度、流式输出、视觉输入、工具调用与 100 万 token 上下文。
- [Kimi K3](https://platform.kimi.com/docs/guide/kimi-k3-quickstart.md): 了解 Kimi K3 的长程编程、知识工作、深度推理、视觉理解与 100 万 token 上下文能力。
- [模型列表](https://platform.kimi.com/docs/models.md): 查看 Kimi 开放平台当前可用的多模态与编程模型,以及已下线模型的迁移提示。
- [思考模型](https://platform.kimi.com/docs/guide/use-thinking-models.md): 了解 Kimi 思考模式的模型选择、`reasoning_content`、多轮保留策略、工具调用和 token 计费。
- [推理强度](https://platform.kimi.com/docs/guide/use-reasoning-effort.md): 使用 `reasoning_effort` 在 `low`、`high` 和 `max` 之间调节 Kimi K3.1 Pro 的推理深度、延迟与 token 消耗。
- [配置多轮对话参数](https://platform.kimi.com/docs/guide/engage-in-multi-turn-conversations-using-kimi-api.md): 在无状态的 Kimi API 中维护消息历史、控制上下文长度,并正确构建多轮对话请求。
- [使用 Kimi API 的流式输出功能](https://platform.kimi.com/docs/guide/utilize-the-streaming-output-feature-of-kimi-api.md): 使用 Kimi API SSE 流式输出降低首 token 等待时间,解析增量响应并获取最终用量数据。
- [使用 Kimi API 的 JSON Mode](https://platform.kimi.com/docs/guide/use-json-mode-feature-of-kimi-api.md): 使用 `response_format` 启用 Kimi API JSON Mode,通过提示词和代码安全获取、解析结构化 JSON 输出。
- [使用 Kimi API 的 Partial Mode](https://platform.kimi.com/docs/guide/use-partial-mode-feature-of-kimi-api.md): 使用 Kimi API Partial Mode 续写给定文本、固定回复开头、继续被截断的输出或保持角色一致性。
- [配置 Kimi 视觉模型](https://platform.kimi.com/docs/guide/use-kimi-vision-model.md): 为 Kimi 多模态模型构建图片和视频输入,支持 base64、URL、文件上传与多图片对话。
- [上下文缓存最佳实践](https://platform.kimi.com/docs/guide/context-caching.md): 了解 Kimi API 上下文缓存的适用场景与计费,提高缓存命中率,选择 5m / 1h 缓存时长(TTL),并查看缓存用量。
- [动态加载工具](https://platform.kimi.com/docs/guide/use-dynamic-tool-loading.md): 按需将工具定义追加到 Kimi 对话中,减少 token 消耗、提高工具选择准确性并保留前缀缓存。
- [使用 Kimi API 完成工具调用(tool_calls)](https://platform.kimi.com/docs/guide/use-kimi-api-to-complete-tool-calls.md): 定义、注册和执行 Kimi API `tool_calls`,回传工具结果并处理流式工具调用。
- [联网搜索最佳实践](https://platform.kimi.com/docs/guide/best-practices-for-web-search.md): 按场景选择搜索接口、控制成本、写有效查询词、配置参数,提升联网搜索结果质量。
- [如何在 Kimi API 中使用官方工具](https://platform.kimi.com/docs/guide/use-official-tools.md): 查看 Kimi 开放平台可用的官方工具,并了解如何在 Chat Completions API 中配置和调用它们。
- [工具调用约束](https://platform.kimi.com/docs/guide/use-tool-choice.md): 使用 `tool_choice` 让 Kimi 自动选择、强制或禁止工具调用,并结合工具定义提高可靠性。
- [Kimi K3 API 工具调用最佳实践](https://platform.kimi.com/docs/guide/kimi-k3-tool-calling-best-practice.md): 工具数量较多时,结合动态加载、tool_choice 与推理强度设计工具调用流程。
- [使用 response_format 控制模型输出格式](https://platform.kimi.com/docs/guide/response_format.md): 使用 `response_format` 启用 JSON Mode 或 Structured Output,并处理模式、结构和 Partial Mode 限制。
- [自动断线重连](https://platform.kimi.com/docs/guide/auto-reconnect.md): 为 Kimi API 流式请求实现断线重连,并结合
…
Published headings
2 indexed headings in this publisher record.
Headings describe indexed content. They do not establish a working integration or endorsement.
Agent access
Review the publisher’s own access terms before automated use.
Machine-readable: GET /v1/resolve?q=kimi.com · GET /v1/domain/kimi.com · this page as Accept: application/json or text/markdown · MCP lookup_domain
Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.
Indexing evidence
Authority, classification and country evidence
Own or manage this website?
If you own or manage kimi.com, you can update its listing and review file health, discovery activity and score history.
Manage this listing — optional
What verification unlocks
See how your site is discovered—and control what agents see.
- See your website in the map
Review your indexed topics, nearby publishers sharing headings, measured listing exposure and map snapshots in a private report for your website.
- Control what agents see
Edit your listing description, tags, public contact details and additional llms.txt paths. Publish your terms for automated access, attribution and pricing.
- Make your profile eligible for search
A valid, listed, unblocked, verified profile can appear in our publisher sitemap and become eligible for search-engine visibility. Search engines decide what to index and rank.
- Appear in our llms-full.txt
Eligible verified publishers are listed by name, with their file links and summaries, in the service overview agents can read.
Free account required for verification and live checks. No backlink or payment required. Public discovery remains available without verification.
Let your coding agent verify it
If your coding agent is authorized to manage this website, paste these instructions into it.
Claim my listing on Agent Web Map for kimi.com:
1. POST https://agentwebmap.com/v1/sites/kimi.com/claims and keep claim_id and claim_secret private.
2. Publish the verification line "AgentWebMap verification: <token>" (token from step 1) in https://kimi.com/llms.txt, or use the DNS, meta-tag or well-known method the response describes. This only verifies the listing; your website and domain remain yours.
3. POST https://agentwebmap.com/v1/sites/kimi.com/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/kimi.com).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verifyCorrections or removal requests: contact the directory.