Model by Moonshot AI

Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship K3.1 model, a post-trained successor to Kimi K3.

Checked 2026-11-05

Kimi K3.1 Pro is Moonshot AI's flagship K3.1 model, a post-trained successor to Kimi K3. It is a natively multimodal agentic model, built for long coding runs and agent work. OpenRouter listed it on 23 October 2026 with a 1,048,576-token context window, text, image and video input, and text output. The headline price is $2 per million input tokens and $10 per million output, checked on 5 November 2026. Providers vary a lot, from $0.40 to $4 on input. The weights are published on Hugging Face under the Kimi K3.1 Pro License, whose text we could not read on the card, so check it before commercial use. The model card gives 2.8 trillion total parameters and 104 billion active, so self-hosting means a large cluster, not one box. That size is the main limit. Most people will call it through Moonshot's API, OpenRouter or one of the other hosts. Our draft flagged it as closed; the sources say open-weight. Figures come from OpenRouter and the Hugging Face card. We have not run it.

Mentioned here

  • Kimi K3

    Kimi K3 is an open-weights model from Moonshot AI, released 2026-07-16, with a 1,048,576-token context and text, image and video input.

    • Open weights

    Moonshot AI, 1M context, $0.19 in / 1M

  • MiniMax M3

    MiniMax M3 is an open-weights model released 2026-05-31, with a 1,048,576-token context and text, image and video input.

    • Open weights

    MiniMax, 1M context, $0.30 in / 1M

  • GLM 5.3

    GLM 5.3 is an open-weights model from Z.ai, released 2026-08-18, with a 1,048,576-token context and text-only input.

    • Open weights

    Zhipu AI (Z.ai), 1M context, $0.07 in / 1M

  • DeepSeek V4 Pro 0813

    DeepSeek V4 Pro 0813 is an open-weights DeepSeek model released 2026-08-12.

    • Open weights

    DeepSeek, 1M context, $0.66 in / 1M

  • OpenRouter

    OpenRouter routes more than 600 models through one API key.

    • Model gateway (router)
    • OpenAI compatible

  • Hugging Face Inference

    Hugging Face Inference Endpoints deploys a model from the Hub onto dedicated, autoscaling hardware.

    • Model / inference API
    • OpenAI compatible

  • Together AI

    Together AI serves open models by the token and also rents GPUs.

    • Model / inference API
    • OpenAI compatible

Questions

What is the context window of Kimi K3.1 Pro?

1,048,576 tokens, with up to 943,718 tokens of output.

How much does Kimi K3.1 Pro cost?

$2 per million input tokens and $10 per million output tokens, checked 31 October 2026.

Can I run Kimi K3.1 Pro on my own hardware?

No. The weights are not published, so you use it through the maker's API or a hosting provider.

Who makes Kimi K3.1 Pro?

Moonshot AI makes it, and released it on 23 October 2026.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Kimi K2.6

    Kimi K2.6 is Moonshot AI's open-weight multimodal model for long coding runs and agent setups, and it is on its way out of Moonshot's own API.

    • Open weights

    Moonshot AI, 262K context, $0.65 in / 1M

  • Kimi K2.7 Code

    Kimi K2.7 Code is Moonshot AI's coding-focused model, aimed at people who want an open-weight agent model that also reads images.

    • Open weights
    • Coding

    Moonshot AI, 262K context, $0.60 in / 1M