Kwaipilot: KAT-Coder-Pro V1

kwaipilot/kat-coder-pro

Created Nov 10, 2025256,000 context

$0.207/M input tokens$0.828/M output tokens

KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark.

The model has been optimized for tool-use capability, multi-turn interaction, instruction following, generalization, and comprehensive capabilities through a multi-stage training process, including mid-training, supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and scalable agentic RL.

Providers for KAT-Coder-Pro V1

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Performance for KAT-Coder-Pro V1

Compare different providers across OpenRouter

Apps using KAT-Coder-Pro V1

Top public apps this month

Recent activity on KAT-Coder-Pro V1

Total usage per day on OpenRouter

Prompt

94.7M

Completion

2.07M

Reasoning

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Uptime stats for KAT-Coder-Pro V1

Uptime stats for KAT-Coder-Pro V1 across all providers

Sample code and API for KAT-Coder-Pro V1

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides an OpenAI-compatible completion API to 400+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.