Back to Models

MoonshotAI: Kimi K2.7 Code (batch)

Moonshotaitext
8.8 / 10 Overall Rating

MoonshotAI Kimi K2.7 Code (batch) is a multimodal coding model designed for asynchronous processing of large codebases. It features a 262K token context window and supports outputs up to 235K tokens at discounted batch rates. It targets automated repository refactoring, multi-file code generation, and visual architecture analysis.

Context Window
262K
Knowledge Cutoff
2025
Max Output
16K
License
Proprietary

Where it Excels (Pros)

  • 262K context with 235K output
  • Cheaper than GPT-4o and Claude
  • Multimodal input for code architecture

Limitations (Cons)

  • High latency from batch execution
  • Weaker general non-coding reasoning

Benchmark Breakdown

Reasoning (MMLU)82%
Coding (HumanEval)78%
Mathematics (MATH)76%
Long-Context Retrieval95%

Pricing Matrix

Input cost / 1M tokens$0.95
Output cost / 1M tokens$4.00

Compare MoonshotAI: Kimi K2.7 Code (batch) with other frontier models:

Related Skills, Tools & Automations