Skip to main content
Glama

kimi-latest-128k vs kimi-k2-0711-preview

Pricing, Performance & Features Comparison

Price unit:
Authormoonshot
Context Length128K
Reasoning
-
Providers1
ReleasedJul 2025
Knowledge Cutoff-
License-

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)2.4s
Output Limit128K
Function Calling
JSON Mode
-
InputText, Image, Audio, Video
OutputText, Audio
in$2out$5cache$0.15-
Latency (24h)
Success Rate (24h)
Authormoonshot
Context Length128K
Reasoning
-
Providers1
ReleasedJul 2025
Knowledge Cutoff-
License-

Kimi-k2-0711-preview is a version of the Kimi K2 language model developed by Moonshot AI. It is a mixture-of-experts model with 32 billion activated parameters and 1 trillion total parameters, optimized for agentic tasks to act, execute, and reason through complex, tool-driven processes. The model is designed for general-purpose chat and autonomous task execution with enhanced coding capabilities.

Input$0.6
Output$2.5
Latency (p50)1.7s
Output Limit128K
Function Calling
JSON Mode
InputText
OutputText, Image
in$0.6out$2.5cache$0.15-
Latency (24h)
Success Rate (24h)