LangMart: MoonshotAI: Kimi Dev 72B
Model Overview
| Property | Value |
|---|---|
| Model ID | openrouter/moonshotai/kimi-dev-72b |
| Name | MoonshotAI: Kimi Dev 72B |
| Provider | moonshotai |
| Released | 2025-06-16 |
Description
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.
Description
LangMart: MoonshotAI: Kimi Dev 72B is a language model provided by moonshotai. This model offers advanced capabilities for natural language processing tasks.
Provider
moonshotai
Specifications
| Spec | Value |
|---|---|
| Context Window | 131,072 tokens |
| Modalities | text->text |
| Input Modalities | text |
| Output Modalities | text |
Pricing
| Type | Price |
|---|---|
| Input | $0.29 per 1M tokens |
| Output | $1.15 per 1M tokens |
Capabilities
- Frequency penalty
- Include reasoning
- Reasoning
- Response format
- Structured outputs
- Temperature
- Top k
- Top p
Detailed Analysis
MoonshotAI: Kimi Dev 72B