Claude Code · Anthropic · DeepSeek · OpenAI · Gemini · Claude · huggingface.co
Kimi K3.1 Pro is launched under the Kimi K3.1 Pro License
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
If you have any questions, please reach out at.
Key facts
- Unless otherwise specified, all Kimi K3.1 Pro results use reasoning effort max, temperature = 1.0, and top-p = 0.95
- You can access Kimi K3.1 Pro's API on by selecting kimi-k3.1-pro, and they provide OpenAI/Anthropic-compatible API for you
- Kimi K3.1 Pro is released under the Kimi K3.1 Pro License
- 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
Summary
Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and their most capable 3T-class model to date. * Compared with Kimi K3, they 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. Kimi K3.1 Pro is evaluated with the Claude Code harness. The DeepSeek-V4.1-Flash-1017 score is taken from its release blog. Terminal-Bench-Science 0.1. Internal evaluation of DeepSeek-V4.1-Flash-1017 yields 9.3; the table instead reports 15.7 for the older DeepSeek-V4.1-Flash from the official leaderboard.