Skip to main content

Kimi on Berges AI

The open-weights model from Moonshot AI, known for long-context reasoning. Pick it from the sidebar and it answers every turn.

Try Kimi

Kimi is a family of large language models from Moonshot AI, whose flagship models have had open weights since K2. The Kimi line is best known for long-context reasoning, and Kimi K3 has a context window of about a million tokens.

Berges AI serves the current Kimi model in its deep-thinking layer. Pick Kimi from the sidebar and it answers every turn, reasoning before each reply; you can open its reasoning while it thinks. Your choice is remembered.

The weights are published openly, which means anyone can audit them, fine-tune them, or host them independently. That auditability is part of why we use it. The license reads like MIT for almost everyone; only very large products and AI services must meet extra conditions.

Kimi specs

Maker: Moonshot AI

License: Kimi K3 license, MIT-style with conditions for very large businesses (open weights)

Architecture: Mixture-of-Experts

Current version: K3

Best known for: Long-context reasoning

What Kimi is good at

Long context

Kimi holds a lot of context without falling apart. Useful when a conversation runs long and the model needs to keep every earlier turn in mind.

Step-by-step reasoning

Multi-step problems where you need to keep state and follow a chain are a Kimi strength. That's exactly what the deep-thinking layer is for.

Multilingual

Kimi is unusually strong on non-English work, particularly Chinese-English, and holds up well across many other languages.

When Kimi is the right pick

  • Long conversations that build on earlier turns
  • Step-by-step reasoning across multiple turns
  • Translation and multilingual writing
  • Tasks where you need the model to "remember" a lot of context

Things people ask about Kimi

Can I use Kimi without Berges AI?

Yes. Moonshot publishes the weights openly. You can run them yourself or use any open-weights host. Berges AI is just one place to chat with Kimi, with privacy as a default and encryption at rest. Very large commercial users (products with over 100 million monthly users or $20 million in monthly revenue, and AI services above $20 million a year) have extra conditions under the Kimi K3 license.

When should I pick Kimi?

When the conversation is long, when the problem has several dependent steps, or when a quick answer feels shallow. Kimi is the largest model we run, so each reply costs more of your plan's units.

Is Kimi the same as ChatGPT?

No. Kimi is an open-weights model from Moonshot AI. ChatGPT runs OpenAI's closed models. Different labs, different weights, different design choices.