Kimi K2
Kimi K2 is a Moonshot AI model family with 2 variants (standard and Thinking) available in Quad Chat, with up to 216K tokens of context, tool calling and step-by-step reasoning.
Kimi K2 at a glance
| Lab | Moonshot AI |
|---|---|
| Available on | Free plan |
| Context window | Up to 216K tokens |
| Max output | Up to 216K tokens |
| Image input | No |
| Tool calling | Yes |
| Reasoning | Yes |
| Privacy lane | Private or Standard, by variant |
Kimi K2 variants
| Model | Context | Plan | API list price per 1M tokens (in / out) |
|---|---|---|---|
| Kimi K2 | 128K | Free plan | $0.57 / $2.30 |
| Kimi K2 Thinking | 216K | Free plan | $0.47 / $2.00 |
How to use Kimi K2 in Quad Chat
- Create a free account or sign in.
- Open the model picker and choose Kimi K2.
- Ask, attach files, or compare the answer with another model.
Frequently asked questions
Can I use Kimi K2 for free?
Yes. Kimi K2 is available on the Quad Chat Free plan, which needs no credit card and includes 100 monthly credits shared across every model. Larger requests use more credits, and paid plans from $8/month raise the allowance.
What is the context window of Kimi K2?
Context windows differ by variant: Kimi K2 128K, Kimi K2 Thinking 216K tokens, according to the model catalog Quad Chat routes through. Files, pasted text and earlier messages all count toward the window.
Does Kimi K2 support images, tools and reasoning?
Kimi K2 works with text input only; pick a vision model in the same chat when you need to attach images. It supports tool calling. It can reason step by step before it answers. You can switch to another model in the same conversation at any time.
Is Kimi K2 private in Quad Chat?
Kimi K2 Thinking runs on the Private Lane with Zero Data Retention routing. Kimi K2 uses the Standard Lane, where the provider may retain prompts, and Quad Chat asks you to confirm first.
How much does Kimi K2 cost in Quad Chat?
Quad Chat plans have a flat monthly price and draw usage from shared credits, not a per-token bill. The model picker shows an estimate before you send. For reference, the provider's API list price is from $0.47 to $0.57 per million input tokens across variants.
Can I compare Kimi K2 with other models?
Yes. Send one prompt to Kimi K2 and one or two other models, such as Kimi K3, Kimi K2.7 Code and Kimi K2.6, and compare the answers side by side in the same thread. You can also switch models mid-conversation without losing your files or context.
Related models
- Kimi K3 — Moonshot AI, Free plan
- Kimi K2.7 Code — Moonshot AI, Free plan
- Kimi K2.6 — Moonshot AI, Free plan
- Kimi K2.5 — Moonshot AI, Free plan
- GPT-6.1 Sol — OpenAI, Pro plan and up
- Gemini 3.8 Flash — Google, Pro plan and up
- Claude Opus 5.5 — Anthropic, Ultra plan and up
- Muse Spark 1.3 — Meta, Free plan