Kimi K3 vs Kimi K2.7 Code
Compare Kimi K3 and Kimi K2.7 Code on key metrics including price, context length, throughput, and other model features.
AuthorMoonShotAI
Context Length1M
Supports Tools
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.
Activity
Last 14 daysPrompt
152MCompletion
1MTotal
153MStartup
Startup
Latency (p50)0.50s
Throughput (p50)9.9 tok/s
Pricing
Input$0.14/M tokens
Output$4.05/M tokens
Cached input$0.03/M tokens
Features
Input Modalitiestext, image
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools
AuthorMoonShotAI
Context Length262.1k
Supports Tools
Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Activity
Last 14 daysPrompt
15MCompletion
203KTotal
15MStartup
Startup
Latency (p50)1.42s
Throughput (p50)38.1 tok/s
Pricing
Input$0.34/M tokens
Output$1.50/M tokens
Cached input$0.07/M tokens
Features
Input Modalitiestext, image
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools