Moonshot AI is an industry-leading pioneer in frontier intelligence, long-context understanding, and deep reasoning models. The platform hosts the complete Kimi API model lineup, led by the flagship Kimi K3 open-weight model. Built on advanced KDA (Delta Attention) architecture and a high-sparsity LatentMoE framework, Kimi K3 delivers a native 1-million-token context window with full multimodal understanding.
Moonshot AI
All Models
Kimi
4 variants available
kimi-k3 3

kimi-k3 2
Kimi K3 is Kimi’s most capable flagship model to date. With 2.8 trillion parameters, it is built on the Kimi Delta Attention (KDA) hybrid linear attention architecture and Attention Residuals technology. It natively supports visual understanding and features a 1-million-token context window. As the world’s first open-source model at the 3-trillion-parameter scale, Kimi K3 is designed for frontier AI use cases, including long-horizon coding, knowledge work, and reasoning.

K3 Custom Edition
Kimi K3 is Kimi’s most capable flagship model to date. With 2.8 trillion parameters, it is built on the Kimi Delta Attention (KDA) hybrid linear attention architecture and Attention Residuals technology. It natively supports visual understanding and features a 1-million-token context window. As the world’s first open-source model at the 3-trillion-parameter scale, Kimi K3 is designed for frontier AI use cases, including long-horizon coding, knowledge work, and reasoning.
Moonshot AI Models API Pricing Details
| Model | Pricing (USD) | Our Pricing (USD) | Discount | |
|---|---|---|---|---|
| kimi-k3 3 | $3/M Tokens | Start from$3/M Tokens | — | |
| kimi-k3 2 | $3/M Tokens | Start from$1.8/M Tokens | -40% | |
| K3 Custom Edition | $3/M Tokens | Start from$1.8/M Tokens | -40% | |
| Kimi K3 | $3/M Tokens | Start from$1.8/M Tokens | -40% |