M

Moonshot AI Models

Browse models from Moonshot AI
Kimi is Moonshot AI's open-source large model series. Kimi K2 was released in 2025, features a 1T parameter MoE architecture, excels at agent tasks, coding, and reasoning, and offers leading performance. - **Adheres to OpenAI Chat format calls**
Kimi K2.6
M

Kimi K2.6

Input:$0.76/M
Output:$3.19998/M
Kimi K2.6 is Kimi's latest and most intelligent model, possessing stronger and more stable long-term code writing capabilities, significantly improved instruction compliance and self-correction abilities, and supporting text, image, and video input, thinking and non-thinking modes, and dialogue and agent tasks.
Kimi K2.5
M

Kimi K2.5

Input:$0.48/M
Output:$2.4/M
Kimi K2.5 is Kimi's most intelligent model to date, achieving open-source SoTA performance in Agent, code, visual understanding, and a range of general intelligent tasks. Kimi K2.5 is also Kimi's most versatile model to date, featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and Agent tasks.
M

Kimi-K2

M

Kimi-K2

Input:$0.48/M
Output:$1.92/M
- **kimi-k2-250905**: Moonshot AI's Kimi K2 series 0905 version, supporting ultra-long context (up to 256k tokens, frontend and Tool calls). - ๐Ÿง  Enhanced Tool Calling: 100% accuracy, seamless integration, suitable for complex tasks and integration optimization. - โšก๏ธ More Efficient Performance: TPS up to 60-100 (standard API), up to 600-100 in Turbo mode, providing faster response and improved Inference capabilities, knowledge cutoff up to mid-2025.