Kimi K2.5
Active Parameters
1T
Context Length
512K
Modality
Text
Architecture
Mixture of Experts (MoE)
License
Modified MIT License
Release Date
5 Feb 2026
Knowledge Cutoff
Oct 2025
API Pricing (per 1M)
Input: $0.60 · Output: $2.75
System Requirements
VRAM requirements for different quantization methods and context sizes
1,024 tokens
Consumer
140x RTX 4090
24GB VRAM
Datacenter
34x NVIDIA A100
80GB VRAM
Apple Silicon
30x Apple M3 Max
128GB VRAM
512,000 tokens
Consumer
234x RTX 4090
24GB VRAM
Datacenter
55x NVIDIA A100
80GB VRAM
Apple Silicon
52x Apple M3 Max
128GB VRAM
Architecture Diagram
Evaluation Benchmarks
Rank
#47
| Benchmark | Score | Rank |
|---|---|---|
Professional Knowledge | 0.871 | 5 |
Software Engineering | 0.71 | 14 |
StackUnseen | 0.649 | 19 |
Graduate-Level QA | 0.876 | 32 |
Web Development | 1436 | 53 |
General Text | auto 1451 Standard 1431 | 54 73 |
Agentic Index | 0.22 | 70 |
Coding Index | 0.47 | 90 |
Intelligence Index | 0.23 | 124 |
Rankings
Overall Rank
#47
Coding Rank
#52
About Kimi K2.5
Kimi K2.5 is a 1T-parameter native multimodal Mixture-of-Experts model from Moonshot AI engineered for complex reasoning and agent swarm orchestration. It supports up to 100 parallel sub-agents and visual coding workflows across a 256K context window.
Technical Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
64
Key-Value Heads
64
Attention Head Dimension
-
Position Embedding
Absolute Position Embedding
RoPE Theta
50,000
Sliding Window Attention
No
Sliding Window Size
-
Sliding Window Ratio
-
Linear Attention
-
Linear Attention Ratio
-
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Hidden Dimension Size
7,168
Number of Layers
61
FFN Intermediate Size (Dense)
2,048
Multi-Token Prediction Heads
0
Tokenizer
Vocabulary Size
163,840
Mixture of Experts
Total Expert Parameters
968.0B
Number of Experts
384
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
2,048
Dense Layers Before MoE
1
About Kimi K2
Moonshot AI's Kimi K2 is a Mixture-of-Experts model featuring one trillion total parameters, activating 32 billion per token. Designed for agentic intelligence, it utilizes a sparse architecture with 384 experts and the MuonClip optimizer for training stability, supporting a 128K token context window.