# Kimi-Dev-72B

> Moonshot AI's open-weight 72B coding model for fixing real software bugs

- Maker: Moonshot AI (Kimi)
- Line: Kimi-Dev
- Canonical page: https://ai-tldr.dev/models/kimi-dev-72b/
- Updated: 2026-06-18

## In short

Kimi-Dev-72B is an open-weight, 72-billion-parameter large language model from Moonshot AI (the team behind Kimi), released on June 16, 2025 and purpose-built for software engineering. It has a 131K-token context window and costs $0.29 per million input tokens and $1.15 per million output tokens. You can use it through OpenRouter.

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 131K | [1] |
| Input price | $0.29 per 1M tokens | [2] |
| Output price | $1.15 per 1M tokens | [2] |
| Licence | MIT · open weights | [1] |
| Released | June 2025 | [3] |
| Parameters | 72B | [1] |
| Knowledge cutoff | Not disclosed | [1] |

## Sources

1. [Hugging Face model card](https://huggingface.co/moonshotai/Kimi-Dev-72B)
2. [OpenRouter API & pricing](https://openrouter.ai/moonshotai/kimi-dev-72b)
3. [Project page](https://moonshotai.github.io/Kimi-Dev/)

## Overview

Kimi-Dev-72B is an open-weight, 72-billion-parameter large language model from Moonshot AI (the team behind Kimi), released on June 16, 2025 and purpose-built for software engineering. Rather than a general chat assistant, Kimi-Dev-72B is tuned for the concrete loop developers live in: reading a bug report or GitHub issue, finding the file that needs to change, writing the fix, and producing unit tests that prove it works.

The model starts from the Qwen2.5-72B base and is shaped in two stages. First, a roughly 150-billion-token mid-training phase exposes it to real GitHub issues and pull-request commits so it learns how human engineers reason about defects. Then large-scale reinforcement learning lets Kimi-Dev-72B autonomously patch real repositories inside Docker containers, earning a reward only when the entire test suite passes — a strict, execution-grounded signal that pushes it toward fixes that actually run.

At launch, Kimi-Dev-72B scored 60.4% on SWE-bench Verified, which Moonshot reported as a new state of the art among open-source models. It is released under the permissive MIT license with full weights on Hugging Face, supports a 131K-token context window, and can be self-hosted through vLLM, SGLang, or Hugging Face Transformers, making it practical for teams that want a capable coding model they fully control.

## Benchmarks

- SWE-bench Verified: 60.4% ([source](https://moonshotai.github.io/Kimi-Dev/))

## Pricing

- Input: $0.29 per 1M tokens
- Output: $1.15 per 1M tokens

Kimi-Dev-72B is open-weight and not sold on Moonshot's first-party API; these are third-party hosting rates on OpenRouter, which also lists a free tier (moonshotai/kimi-dev-72b:free). Self-hosting cost is your own compute.

Source: https://openrouter.ai/moonshotai/kimi-dev-72b

## Strengths

- State-of-the-art open-source result on SWE-bench Verified (60.4%) at its June 2025 release
- Permissive MIT license with full open weights — unrestricted commercial and private use
- Trained with execution-grounded RL: rewarded only when a patch passes the full Docker test suite, favoring fixes that genuinely run
- 131K-token context handles large files and multi-file repository tasks
- Self-hostable via vLLM, SGLang, and Transformers, with broad community quantizations (GGUF, GPTQ, MLX) for local use

## Best for

- Automated bug fixing and GitHub issue resolution against real repositories
- Generating and repairing unit tests for changed code
- Fault localization — pinpointing which file or function needs editing
- Code review and patch suggestion inside engineering workflows
- Self-hosted, license-clean coding assistant for teams that need on-prem control

## How to access

- [OpenRouter](https://openrouter.ai/moonshotai/kimi-dev-72b) — model id `moonshotai/kimi-dev-72b`

## Kimi-Dev versions

- Kimi-Dev-72B (June 2025) — this page

## FAQ

### What is Kimi-Dev-72B?

Kimi-Dev-72B is an open-weight, 72-billion-parameter coding model from Moonshot AI, released June 16, 2025. It is built on Qwen2.5-72B and specialized for software engineering tasks like bug fixing, GitHub issue resolution, and unit-test generation.

### How well does Kimi-Dev-72B perform on SWE-bench?

It scores 60.4% on SWE-bench Verified, which Moonshot AI reported as a state-of-the-art result among open-source models at its release.

### Is Kimi-Dev-72B open source and free to use?

Yes. The full weights are published on Hugging Face under the permissive MIT license, allowing commercial and private use. You can self-host it, and hosted access is available on OpenRouter, which also offers a free tier.

### What context length does Kimi-Dev-72B support?

It supports a 131K-token (128K) context window, enough for large source files and multi-file repository tasks. The model is text-only and can be served with vLLM, SGLang, or Hugging Face Transformers.

## Links

- [Hugging Face model card](https://huggingface.co/moonshotai/Kimi-Dev-72B)
- [Project page](https://moonshotai.github.io/Kimi-Dev/)
- [GitHub repository](https://github.com/MoonshotAI/Kimi-Dev)
- [OpenRouter API & pricing](https://openrouter.ai/moonshotai/kimi-dev-72b)
- [SWE-bench Verified leaderboard](https://www.swebench.com/)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/kimi-dev-72b/