Moonshotaitext->text

MoonshotAI: Kimi Dev 72B

Kimi-Dev-72B is an open-source large language model fine-tuned for software engineering and issue resolution tasks. Based on Qwen2.5-72B, it is optimized using large-scale reinforcement learning that applies code patches in real repositories and validates them via full test suite execution—rewarding only correct, robust completions. The model achieves 60.4% on SWE-bench Verified, setting a new benchmark among open-source models for software bug fixing and code reasoning.

Context Window

131K

Input Price

$0.2900/M tokens

Output Price

$1.15/M tokens

Modality

text->text

Pricing Breakdown

Cost per million tokens for input and output

Input$0.2900/M tokens

Output$1.15/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.004050

Context Window Size

Maximum tokens the model can process in a single request

Context Window131K tokens

13% of 1M max

~98K

Words Equivalent

~66

Pages of Text

~1311

Code Functions

Best Use Cases

What this model excels at

CodingProgrammingDevelopmentMathReasoningAnalysis

Related Categories:

Data Analysis

Test MoonshotAI: Kimi Dev 72B Now

Compare this model with others using your own prompts

Ready to Test MoonshotAI: Kimi Dev 72B?

Use our free AI Models Tester to compare MoonshotAI: Kimi Dev 72B with other models side-by-side using your own prompts. See real results instantly.