kimi-latest-128k vs kimi-latest-8k
Pricing, Performance & Features Comparison
Kimi-latest-128k refers to the Kimi K2 model, a state-of-the-art Mixture-of-Experts (MoE) language model with 32 billion activated and 1 trillion total parameters. It features a 128K context length and is meticulously optimized for agentic capabilities, specifically designed for tool use, reasoning, and autonomous problem-solving.
Input$2
Output$5
Latency (p50)-
Output Limit128K
Function Calling
JSON Mode
-
InputText, Image, Audio, Video
OutputText, Audio
in$2out$5cache$0.15-
Success Rate (24h)
Kimi-latest-8k is a variant of the Kimi K2 model series, a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. It is designed for frontier knowledge, reasoning, and coding tasks while being optimized for agentic capabilities including tool use and autonomous problem-solving.
Input$0.2
Output$2
Latency (p50)-
Output Limit8K
Function Calling
JSON Mode
-
InputText, Image, Audio, Video
OutputText
in$0.2out$2cache$0.15-