Kimi K2.7 Code vs Kimi K3
Compare Kimi K2.7 Code and Kimi K3 on key metrics including price, context length, throughput, and other model features.
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
12MCompletion
92KTotal
12MStartup
Startup
Latency (p50)0.84s
Throughput (p50)40.9 tok/s
Pricing
Input$0.34/M tokens
Output$1.70/M tokens
Cached input$0.10/M tokens
Features
Input Modalitiestext, image
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools
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
10MCompletion
521KTotal
11MStartup
Startup
Latency (p50)4.50s
Throughput (p50)16.7 tok/s
Pricing
Input$1.50/M tokens
Output$7.50/M tokens
Cached input$0.15/M tokens
Features
Input Modalitiestext, image
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools