
MoonshotAI: Kimi K3 (batch)
moonshotai/kimi-k3:batch
模型权重Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
提供商
不同公司托管同一模型。OpenRouter 根据您选择的路由模式将请求路由到其中一家公司:Balanced(价格 + 速度)、Nitro(速度最快)或 Floor(价格最低)。
| US$2.28 | US$11.40 | US$0.228 | -- | -- |
输入 US$2.28 / 输出 US$11.40-- tok/s-- 正常运行时间
定价
客户为此模型实际支付的平均价格,与提供商公布的价格并列展示。由于缓存和折扣,实际支付的价格往往远低于标价。
加权平均值
Kimi K3 (batch) — 价格历史
| US$0.00 | US$0.00 | 0.0% | 100.0% |
- 有效输入价格 US$0.00 / 实际输出 US$0.00token 占比100.0%
性能
吞吐量是模型生成内容的速度(每秒 token 数,越高越好)。延迟是完整的往返时间(越低越好)。TTFT 是首个 token 的响应时间,即您看到内容出现前需要等待的时间(越低越好)。
正常运行时间
正常运行时间是指过去 3 天中至少有一家提供商响应请求的时间百分比。可用性是指成功提供推理服务的时间百分比。OpenRouter 会持续监控,并在某家提供商返回错误时使用次优提供商。
正常运行时间数据尚不足,暂时无法显示。
当上游提供商发生错误时,如果您的请求筛选条件允许,我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据: 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。
基准测试
标准化评测得分,以及此模型针对共用基准测试提示词的实际输出。百分比越高越好,每项排名显示此模型在该来源所评测的模型中的位置。
| 来源 | 基准测试 | 得分 |
|---|---|---|
| Artificial Analysis | Kimi K3 (Max) Coding Index | 76.2 |
| Artificial Analysis | Kimi K3 (Max) Agentic Index | 50.0 |
| Artificial Analysis | Kimi K3 (Max) GPQA Diamond | 93.5% |
| Artificial Analysis | Kimi K3 (Max) HLE | 46.9% |
| Artificial Analysis | Kimi K3 (Max) AA-LCR | 88.7% |
| Artificial Analysis | Kimi K3 (Max) τ-Bench Banking | 46.0% |
| Artificial Analysis | Kimi K3 (Max) GDPval-AA | 52.1% |
| Artificial Analysis | Kimi K3 (Max) CritPt | 23.4% |
| Artificial Analysis | Kimi K3 (Max) SciCode | 59.5% |
| Artificial Analysis | Kimi K3 (Max) Terminal-Bench 4.0 | 12.6% |
| Artificial Analysis | Kimi K3 (Max) Terminal-Bench 2.1 | 85.0% |
| Artificial Analysis | Kimi K3 (Low) Intelligence Index | 17.4 |
| Artificial Analysis | Kimi K3 (Low) Coding Index | 72.0 |
| Artificial Analysis | Kimi K3 (Low) Agentic Index | 29.3 |
| Artificial Analysis | Kimi K3 (Low) GPQA Diamond | 84.2% |
| Artificial Analysis | Kimi K3 (Low) HLE | 25.0% |
| Artificial Analysis | Kimi K3 (Low) AA-LCR | 79.3% |
| Artificial Analysis | Kimi K3 (Low) τ-Bench Banking | 41.6% |
| Artificial Analysis | Kimi K3 (Low) GDPval-AA | 31.8% |
| Artificial Analysis | Kimi K3 (Low) CritPt | 3.1% |
| Artificial Analysis | Kimi K3 (Low) SciCode | 52.7% |
| Artificial Analysis | Kimi K3 (Low) Terminal-Bench 4.0 | 12.6% |
| Artificial Analysis | Kimi K3 (Low) Terminal-Bench 2.1 | 82.4% |
| Artificial Analysis | Kimi K3 (Low) AA-Omniscience Accuracy | 42.4% |
| Artificial Analysis | Kimi K3 (Low) AA-Omniscience Non-Hallucination Rate | 23.4% |
| Design Arena | Kimi K3 Agents Arena Agenticgamedev Elo | 1198 |
| Design Arena | Kimi K3 Agents Arena Androidnative Elo | 1257 |
| Design Arena | Kimi K3 Agents Arena Blender3d Elo | 1147 |
| Design Arena | Kimi K3 Agents Arena Codetovideo Elo | 1279 |
| Design Arena | Kimi K3 Agents Arena Full Stack Elo | 1289 |
| Design Arena | Kimi K3 Agents Arena Godotgamedev Elo | 1199 |
| Design Arena | Kimi K3 Agents Arena Htmlslides Elo | 1153 |
| Design Arena | Kimi K3 Agents Arena Mobile Apps Elo | 1253 |
| Design Arena | Kimi K3 Agents Arena Pdf Elo | 1277 |
| Design Arena | Kimi K3 Agents Arena Python-Pptxslides Elo | 1223 |
| Design Arena | Kimi K3 Agents Arena Spreadsheet Elo | 1070 |
| Design Arena | Kimi K3 Agents Arena Webapps Elo | 1274 |
| Design Arena | Kimi K3 Models Arena 3D Elo | 1364 |
| Design Arena | Kimi K3 Models Arena Asciiart Elo | 1352 |
| Design Arena | Kimi K3 Models Arena Code Categories Elo | 1351 |
| Design Arena | Kimi K3 Models Arena Data Visualization Elo | 1349 |
| Design Arena | Kimi K3 Models Arena Game Development Elo | 1353 |
| Design Arena | Kimi K3 Models Arena SVG Elo | 1295 |
| Design Arena | Kimi K3 Models Arena UI Component Elo | 1342 |
| Design Arena | Kimi K3 Models Arena Website Elo | 1336 |
| Vals AI | Kimi K3 Access to Justice Benchmark | 68.2% |
| Vals AI | Kimi K3 BioMysteryBench | 72.6% |
| Vals AI | Kimi K3 Code Migration v1.1 | 28.6% |
| Vals AI | Kimi K3 CorpFin v2 | 71.6% |
| Vals AI | Kimi K3 CyberBench v1.1 | 75.2% |
| Vals AI | Kimi K3 CyberOffense | 25.0% |
| Vals AI | Kimi K3 EMB v1.1 | 71.3% |
| Vals AI | Kimi K3 Finance Agent v2.1 | 60.0% |
| Vals AI | Kimi K3 Vals Finance Index | 58.0% |
| Vals AI | Kimi K3 Financial Coaching Bench | 74.5% |
| Vals AI | Kimi K3 GPQA Diamond | 92.9% |
| Vals AI | Kimi K3 HLAB-Vals-1.1 | 12.9% |
| Vals AI | Kimi K3 Immigration | 68.3% |
| Vals AI | Kimi K3 Vals Inference Provider Index | 64.9% |
| Vals AI | Kimi K3 IOI | 48.9% |
| Vals AI | Kimi K3 LiveCodeBench | 87.2% |
| Vals AI | Kimi K3 LegalBench | 86.2% |
| Vals AI | Kimi K3 Vals Legal Index | 71.7% |
| Vals AI | Kimi K3 Legal Research Bench | 46.2% |
| Vals AI | Kimi K3 MedCode | 49.4% |
| Vals AI | Kimi K3 MedScribe | 88.0% |
| Vals AI | Kimi K3 MMLU Pro | 88.0% |
| Vals AI | Kimi K3 MMMU Pro | 88.2% |
| Vals AI | Kimi K3 MortgageTax | 66.3% |
| Vals AI | Kimi K3 ProgramBench | 2.0% |
| Vals AI | Kimi K3 ProofBench v1.1 | 87.0% |
| Vals AI | Kimi K3 Public Benefits Bench v1.1 | 68.2% |
| Vals AI | Kimi K3 Vals RSI Index | 20.9% |
| Vals AI | Kimi K3 SAGE | 86.8% |
| Vals AI | Kimi K3 SWE-bench | 93.4% |
| Vals AI | Kimi K3 SWE-bench Multimodal | 44.2% |
| Vals AI | Kimi K3 Tax Agent Bench | 33.4% |
| Vals AI | Kimi K3 TaxEval v2 | 75.7% |
| Vals AI | Kimi K3 Terminal-Bench 4.0 | 17.2% |
| Vals AI | Kimi K3 Terminal-Bench-Science | 1.4% |
| Vals AI | Kimi K3 Vals Index | 53.0% |
| Vals AI | Kimi K3 Vals Multimodal Index | 73.4% |
| Vals AI | Kimi K3 Vibe Code Bench 1-100 | 18.2% |
| Vals AI | Kimi K3 Vibe Code Bench v1.1 | 85.0% |
应用
向此模型发送最多流量的公开应用。这能很好地反映实际生产工作负载的情况,也能提示此模型最适合哪些用例。
使用此模型的应用尚无足够数据。
活动
此模型的 token 用量和请求流量随时间的变化。
API
可直接用于调用此模型的代码。OpenRouter 的 API 与 OpenAI 兼容——大多数 SDK 只需替换基础 URL 即可使用。切换模型时,唯一需要更改的是下方的模型标识符。
目前无法通过 EU 区域内路由使用。 区域内路由文档
文档
在 OpenRouter 上使用 MoonshotAI: Kimi K3 (batch) 构建应用的指南、实用教程、博客文章和工具。
常见问题
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
OpenRouter 上的 Kimi K3 (batch) 文档包括 Open-Weight vs Closed-Weight Models: What's the Difference? 博客文章。快速入门介绍了 API 密钥和您的首次请求,API 参考列出了所有参数。
Kimi K3 (batch) 的费用为 US$2.28/百万输入 token 和 US$11.40/百万输出 token,Cache Read,价格为 US$0.228/M tokens 单独计费。
Kimi K3 (batch) 的上下文窗口为 1,048,576 个 token。它最多支持 16,384 个补全 token。
是的。Kimi K3 (batch) 接受 tools 和 tool_choice,以进行函数调用。 它还支持通过 response_format 中的 JSON schema 实现结构化输出。
Kimi K3 (batch) 接受 文本、图像和视频 作为输入,并返回 文本。
在 OpenRouter 上,Kimi K3 (batch) 由 1 家提供商提供服务:DeepInfra。
Kimi K3.1 Pro, Kimi K2.7 Code, Kimi K2.6 及另外 4 个 是 MoonshotAI 的其他 文本 模型。
Kimi K3 (batch) 于 2026年7月16日 发布。