Skip to main content
Glama

claude-sonnet-4-6 vs kimi-k2.5

Pricing, Performance & Features Comparison

Authoranthropic
Context Length1M
Reasoning
-
Providers1
ReleasedFeb 2026
Knowledge CutoffAug 2025
License-

Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, delivering frontier performance across coding, agents, and professional work at scale. It features advanced capabilities including extended and adaptive thinking, supports a 1M token context window, and excels in reasoning, coding, multilingual tasks, long-context handling, and image processing with a training data cutoff of January 2026.

Input$3
Output$15
Latency (p50)2.3s
Output Limit128K
Function Calling
JSON Mode
InputText, Image
OutputText
in$3out$15--
Latency (24h)
Success Rate (24h)
Authormoonshot
Context Length262K
Reasoning
-
Providers1
ReleasedJan 2026
Knowledge CutoffApr 2024
License-

Kimi K2.5 is Moonshot's most intelligent and versatile model to date, featuring a native multimodal architecture that supports both visual and text input alongside thinking and non-thinking modes. It achieves state-of-the-art performance in coding, reasoning, and Agent tasks, utilizing a 256K context window to solve complex logical and mathematical problems.

Input$0.6
Output$3
Latency (p50)4s
Output Limit96K
Function Calling
JSON Mode
-
InputText, Image, Video
OutputText
in$0.6out$3cache$0.1-
Latency (24h)
Success Rate (24h)