kimi-k2-0905-preview vs gemini-2.5-flash-preview-09-2025
Pricing, Performance & Features Comparison
Context Length256K
Reasoning
-
Providers1
ReleasedSep 2025
Knowledge CutoffFeb 2023
License–
Kimi K2 is our latest Mixture-of-Experts model with 32 billion activated parameters and 1 trillion total parameters.
Input$0.6
Output$2.5
Latency (p50)–
Output Limit–
Function Calling
JSON Mode
-
Input–
Output–
in$0.6out$2.5cache$0.15–
Gemini 2.5 Flash is our best model in terms of price and performance, and offers well-rounded capabilities.
Input$0.15
Output$0.6
Latency (p50)–
Output Limit–
Function Calling
JSON Mode
-
Input–
Output–
in$0.15out$0.6––