Vision
Moonshot
Claude 3.7 Sonnet
Frontier
Claude 3.7 Sonnet (high output)
Frontier
Claude 3.7 Sonnet (thinking)
Frontier
Claude 4 Opus
Frontier
Claude 4 Opus (thinking)
Frontier
Claude 4 Sonnet
Frontier
Claude 4 Sonnet (thinking)
Frontier
Claude 4.5 Haiku
Frontier
Claude 4.5 Opus
Frontier
Claude 4.5 Opus (High)
Frontier
Kimi K2.5
Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Mixture-of-Experts with 1 trillion parameters.
Model Specifications
Context window
256,000 tokens
Max output
32,768 tokens
Knowledge cutoff
June 2025
Multipart messages
No
Vision capabilities
Yes
Default Parameters
Temperature
0.6
Top P
1.0
Frequency penalty
0.0
Presence penalty
0.0
Top K
40
More models from Moonshot
Kimi K2
Kimi K2 (0905) is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Hosted in the USA.
Context: 256,000
Output: 16,384
Kimi K2 (thinking)
Kimi K2 thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, it was built as a thinking agent that reasons step-by-step while dynamically invoking tools.
Context: 256,000
Output: 16,384