Moonshot AI has released Kimi K3.1 Pro, the first model in its K3.1 series. This open-weight model features 2.8 trillion total parameters and 104 billion active parameters using a Mixture of Experts (MoE) architecture, with a 1-million-token context window.
Key points
- Kimi K3.1 Pro has 2.8T total and 104B active parameters.
- The model features a 1-million-token context window.
- It competes with proprietary models on coding benchmarks.
- Kimi K3.1 Pro scores 65.7% on Terminal-Bench 4.0.
- It leads SWE-Marathon benchmark with 51.7%.
The Kimi K3.1 Pro is positioned to compete with strong proprietary models on coding, agentic, and knowledge benchmarks. While open weights are anticipated for release in November 2026, API access is available now.
The model is a post-trained version of Kimi K3, enhanced with significantly larger post-training compute and joint reinforcement learning across numerous domains. The Moonshot team optimized its RL framework, long-context inference, sandbox infrastructure, and rollout scheduling.
By the numbers
- Total parameters
- 2.8T
- Active parameters (MoE)
- 104B
- Token context window
- 1M
The base K3 architecture incorporates Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), activating 16 out of 896 experts via a Stable LatentMoE framework. The API supports text, image, and video inputs.
Kimi K3.1 Pro Highspeed, a faster version, runs 2 to 3 times quicker. On benchmarks, K3.1 Pro scores 65.7% on Terminal-Bench 4.0, closely trailing Claude Opus 5.5 at 66.4%. It leads on SWE-Marathon with 51.7%, surpassing Opus 5.5's 46.3%.
Sources and references
Original report
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context
MarkTechPost
Read on MarkTechPost (opens in a new tab)Linked in the original report
Ref 00E4UL0V
Cite this
APA
Interestana AI Editorial. (2026, October 23). Moonshot AI Releases Kimi K3.1 Pro Model. Interestana. https://interestana.com/articles/moonshot-ai-releases-kimi-k31-pro-a-28t-total104b-active-params-moe-model-with-1m-context-00e4ul0v
MLA
“Moonshot AI Releases Kimi K3.1 Pro Model.” Interestana, 23 Oct. 2026, interestana.com/articles/moonshot-ai-releases-kimi-k31-pro-a-28t-total104b-active-params-moe-model-with-1m-context-00e4ul0v.
Chicago
Interestana AI Editorial. “Moonshot AI Releases Kimi K3.1 Pro Model.” Interestana, October 23, 2026. https://interestana.com/articles/moonshot-ai-releases-kimi-k31-pro-a-28t-total104b-active-params-moe-model-with-1m-context-00e4ul0v.
BibTeX
@misc{interestana_00e4ul0v,
author = {{Interestana AI Editorial}},
title = {{Moonshot AI Releases Kimi K3.1 Pro Model}},
howpublished = {Interestana},
year = {2026},
month = oct,
url = {https://interestana.com/articles/moonshot-ai-releases-kimi-k31-pro-a-28t-total104b-active-params-moe-model-with-1m-context-00e4ul0v},
note = {Summary of reporting by MarkTechPost, https://www.marktechpost.com/2026/10/23/moonshot-ai-kimi-k3-1-pro-open-weight-model/}
}Credit the source
Original reporting: MarkTechPost, “Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context”, https://www.marktechpost.com/2026/10/23/moonshot-ai-kimi-k3-1-pro-open-weight-model/(opens in a new tab)
Follow this story
Get Artificial Intelligence in your inbox — new stories in 40 words or fewer, once a week.
Subscribe