moonshotai/Kimi-K3.1-Pro
类型 image-text-to-text · 框架 transformers · 下载 30,721 · 收藏 1,867
类型 image-text-to-text · 框架 transformers · 下载 30,721 · 收藏 1,867
定位:Kimi K3.1 Pro 是 Moonshot AI 推出的开放权重原生多模态 Agent 模型,K3.1 系列首款,主打百万级上下文下的编程与多模态任务。 核心能力
适用人群:适合构建 Agent、编程与金融研究工具的开发者,需要长上下文和多模态输入;通过 transformers 加载,自备推理硬件,并遵守自定义许可。 注意:采用自定义 kimi-k3.1-pro 许可,非标准开源协议。
位置づけ:Kimi K3.1 Pro は Moonshot AI が公開したオープンウェイトのネイティブマルチモーダルエージェントモデルで、K3.1 シリーズの第 1 弾。100 万級コンテキストでのプログラミングとマルチモーダルタスクを主眼とする。 主な機能
向いている人:長いコンテキストとマルチモーダル入力が必要な、エージェント、プログラミング、金融リサーチツールを構築する開発者。transformers で読み込み、推論用ハードウェアは自前で用意し、カスタムライセンスを遵守すること。 注意:標準的なオープンソースライセンスではなく、カスタムの kimi-k3.1-pro ライセンスを採用している。
정의: Kimi K3.1 Pro는 Moonshot AI가 공개한 오픈 웨이트 네이티브 멀티모달 에이전트 모델로, K3.1 시리즈의 첫 번째 모델이다. 백만 단위 컨텍스트에서의 프로그래밍과 멀티모달 작업을 주력으로 한다. 핵심 기능
대상: 긴 컨텍스트와 멀티모달 입력이 필요한 에이전트, 프로그래밍, 금융 리서치 도구를 만드는 개발자. transformers로 로드하고 추론 하드웨어를 직접 마련해야 하며, 사용자 지정 라이선스를 준수해야 한다. 주의: 표준 오픈소스 라이선스가 아닌 사용자 지정 kimi-k3.1-pro 라이선스를 사용한다.
What it is: Kimi K3.1 Pro is Moonshot AI's open-weight, natively multimodal agentic model, the first release in the K3.1 series, built for long-context coding and multimodal agent work. Key capabilities
Who it is for: Developers building agent, coding, 3D-creation or financial-research tools that need long context and image input.
来源 · 查看原文
tags:
license: other licensename: "kimi-k3.1-pro" libraryname: transformers pipeline_tag: image-text-to-text ---
📰 Tech Blog | 🚀 API Quickstart
Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series. With a 1-million-token context window, Kimi K3.1 Pro delivers substantial improvements in coding, 3D creation, financial research, factual accuracy, and other agentic capabilities.
| Architecture | Mixture-of-Experts (MoE) |
| Total Parameters | 2.8T |
| Activated Parameters | 104B |
| Number of Layers | 93 |
| Number of Dense Layers | 1 |
| Attention-Layer Composition | 69 KDA + 24 Gated DSA* |
| Attention Hidden Dimension | 7168 |
| Number of Attention Heads | 96 |
| DSA Index Head Dimension | 128 |
| DSA Index Number of Heads | 32 |
| DSA Index Top-K | 2048 |
| Latent MoE Dimension | 3584 |
| MoE Hidden Dimension (per Expert) | 3072 |
| Number of Experts | 896 |
| Selected Experts per Token | 16 |
| Number of Shared Experts | 2 |
| Vocabulary Size | 160K |
| Context Length | 1048576 |
| Attention Mechanism | KDA & Gated DSA |
| Activation Function | SiTU-GLU |
| Vision Encoder | MoonViT-V2 |
| Parameters of Vision Encoder | 401M |
| Quantization | MXFP4 weights / MXFP8 activations (quantization-aware training) |
| Modality | Text, Image |
* Compared with Kimi K3, we replace the full-attention Gated MLA layers with Gated DeepSeek Sparse Attention (Gated DSA) layers for more efficient long-context modeling.
Unless otherwise specified, all Kimi K3.1 Pro results use reasoning effort max, temperature = 1.0, and top-p = 0.95. A dash (—) means that the source table does not report a score. Higher scores are better except where the benchmark name explicitly states lower is better; Elo scores and other benchmark-specific metrics are not directly comparable with accuracy or pass-rate scores.
| Benchmark | Kimi K3.1 Pro (max) |
Claude Fable 5.1 (max, w/ fallback) |
GPT-6 Astra (max, w/ fallback) |
Claude Opus 5.5 (max, w/ fallback) |
DeepSeek-V4.1-Flash-1017 (max) |
GLM-5.3 (max) |
|---|---|---|---|---|---|---|
| Coding | ||||||
| Terminal-Bench 4.0 | 65.7 | 57.9 | 58.2 | 66.4 | 42.3 | 41.8 |
| Terminal-Bench-Science 0.1 | 38.1 | 40.0 | 68.1 | 63.3 | 15.7 | 8.1 |
| SWE Marathon v1.1 | 51.7 | 45.6 | 42.5 | 46.3 | 40.0 | 42.5 |
| BenchCAD w/o tools | 72.8 | 60.6 | — | 73.0 | 41.2 | — |
| BenchCAD w/ tools | 92.7 | 92.6 | 95.9 | 96.2 | 81.6 | — |
| Program Bench | 31.5 | 53.5 | 50.0 | 65.0 | 29.1 | 19.0 |
| DeepSWE v1.1 | 75.5 | 67.4 | 74.1 | 74.2 | 77.0 | 66.9 |
| PostTrain Bench v1.2 | 36.5 | 44.6 | 41.9 | 43.8 | 30.5 | 34.5 |
| Kimi Code Bench 2.0 (Internal) | 77.1 | — | — | — | 76.1 | 61.7 |
| Kimi Code Bench 3.0 Long-horizon (Internal) | 61.2 | 58.8 | 66.5 | 58.5 | 51.5 | 45.5 |
| Agentic | ||||||
| HLE-Full w/ tools | 70.0 | 65.6 | 57.2 | 67.7 | 58.8 | 62.5 |
| BrowseComp | 92.1 | — | 91.5 | 90.8 | — | — |
| BioMysteryBench | 80.6 | 81.6 | 78.9 | 81.9 | 80.0 | 79.6 |
| CharXiv (RQ) w/ python | 93.4 | 92.7 | 92.8 | 93.8 | 85.6 | — |
| MMMU-Pro w/ python | 90.0 | 88.4 | 87.8 | 89.8 | 82.5 | — |
| GDP.pdf w/ python | 85.7 | 83.8 | 85.5 | 83.9 | 73.0 | — |
| ChartoGraphy w/ python | 90.2 | 88.4 | 91.0 | 89.0 | 83.0 | — |
| BabyVision w/ python | 95.4 | 95.1 | 96.6 | 97.7 | 92.5 | — |
| ZeroBench_main w/ python (pass@5) | 63.0 | 59.0 | 58.0 | 61.0 | 51.0 | — |
| Agents' Last Exam (ALL) | 43.2 | — | 41.8 | 42.6 | 37.7 | 26.2 |
| Agents' Last Exam (CLI) | 44.2 | — | 44.2 | 40.7 | 36.0 | 29.4 |
| Automation Bench-AA | 73.3 | 59.4 | 68.5 | 69.5 | 66.6 | 62.2 |
| GDPval-AA v2.1 (Elo-score) | 1846 | 1754 | 1573 | 1866 | 1746 | 1650 |
| AA-Briefcase v1.1 (Elo-score) | 1678 | 1672 | 1569 | 1803 | 1570 | 1507 |
| APEX-Agents | 69.4 | 68.6 | 64.7 | 73.5 | 69.8 | 56.6 |
| OfficeQA Pro v2 | 64.4 | 54.5 | 54.4 | 62.2 | 40.4 | 31.1 |
| OfficeQA Pro | 67.4 | 68.6 | 66.2 | — | 62.4 | 58.6 |
| Frontier Finance | 58.6 | 60.8 | 45.0 | 56.7 | 54.5 | 57.5 |
| Harvey Legal Agent | 23.7 | 19.1 | — | — | 21.0 | — |
| HANDBOOK.md | 44.6 | 38.8 | — | 41.5 | 28.9 | 20.8 |
| OSWorld V2.1 | 79.6 | 80.7 | 75.8 | 81.8 | 69.3 | — |
| Business Operation (Internal) | 37.8 | 30.7 | 32.3 | — | 8.9 | 18.6 |
| DECK-Arena (Internal, Elo-score) | 1456 | — | 1423 | 1253 | 1231 | 1119 |
| Design Bench (Internal, Elo-score) | 957 | — | 1076 | 927 | 863 | 718 |
| Kimi Hallu Bench Hard w/ tools (Internal, lower is better) | 8.3 | 23.3 | 5.5 | 15.0 | 23.3 | 22.6 |
| Reasoning & Knowledge & Multimodal | ||||||
| GDP.pdf | 34.6 | 27.6 | 34.2 | 30.6 | 17.2 | 11.2 |
| HLE-Full | 51.1 | 57.6 | 53.6 | 59.8 | 42.6 | 43.0* |
| HLE-Diamond | 39.4 | 55.1 | 65.8 | 60.9 | 21.6 | 25.1* |
| GPQA-Diamond | 94.2 | 93.7 | 96.1 | 93.9 | 92.2 | 91.7 |
| CharXiv (RQ) | 89.0 | 88.8 | 90.0 | 92.1 | 77.0 | — |
| MMMU-Pro | 84.1 | 86.3 | 86.9 | 87.7 | 80.6 | — |
| ZeroBench_main (avg@5 / pass@5) | 29.8 / 39.0 | 23.0 / 35.0 | 43.2 / 52.0 | 35.0 / 43.0 | 11.8 / 23.0 | — |
| PerceptionBench | 68.3 | 63.0 | 77.6 | 72.1 | 47.7 | — |
| Kimi Hallu Bench w/o tools (Internal, lower is better) | 5.4 | 11.4 | 4.2 | 6.8 | 13.1 | 14.8 |
| Cyber Security | ||||||
| ExploitBench | 74.7 | 83.0 | 100 | 91.0 | — | 54.4 |
| ExploitGym | 20.7 | 30.4 | 42.4 | 34.5 | — | 15.0 |
| xdev-bench-hard (Internal) | 81.0 | — | — | — | 85.7 | 57.1 |
temperature = 1.0 and top-p = 1.0.*, accuracy is reported on the text-only subset.[!Note] You can access Kimi K3.1 Pro's API on https://platform.kimi.ai by selecting kimi-k3.1-pro, and we provide OpenAI/Anthropic-compatible API for you. Currently, Kimi K3.1 Pro is recommended to run on the following inference engines:
The thinking effort of Kimi K3.1 Pro is configured with the top-level reasoning_effort request field, which supports "low", "high", and "max" (default "max").
For multi-turn conversations and tool calls, Kimi K3.1 Pro requires the complete assistant message returned by the API to be passed back to messages as-is — including reasoning_content and tool_calls, not just content:
import openai
def chat_with_preserved_thinking(client: openai.OpenAI, model_name: str):
messages = [
{
"role": "user",
"content": "Tell me three random numbers."
},
{
"role": "assistant",
"reasoning_content": "I'll start by listing five numbers: 473, 921, 235, 215, 222, and I'll tell you the first three.",
"content": "473, 921, 235"
},
{
"role": "user",
"content": "What are the other two numbers you have in mind?"
}
]
response = client.chat.completions.create(
model=model_name,
messages=messages,
stream=False,
max_tokens=4096,
reasoning_effort="max",
)
# the assistant should mention 215 and 222 that appear in the prior reasoning content
print(f"response: {response.choices[0].message.reasoning}")
return response.choices[0].message.content
For full guides and examples (vision input, structured output, partial mode, tool choice, dynamic tool loading, context caching), see the Kimi K3.1 Pro Quickstart and Thinking Effort.
Kimi K3.1 Pro is released under the Kimi K3.1 Pro License.
If you have any questions, please reach out at support@moonshot.ai.