Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube

The free endpoint has reduced rate limits from January 5-12, after which it will be deprecated. Use kwaipilot/kat-coder-pro-v1(opens in new tab) for continued access.

Favicon for kwaipilot

Kwaipilot: KAT-Coder-Pro V1

kwaipilot/kat-coder-pro

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.

Modalities

Context

262K

Released

Nov 10, 2025

ActivityFAQExplore

Activity

Token volume and request traffic to this model over time.

Explore models like this

AI Model RankingsRanking

About Kwaipilot: KAT-Coder-Pro V1

OpenRouter makes Kwaipilot: KAT-Coder-Pro V1 available through a unified, OpenAI-compatible API using the model ID kwaipilot/kat-coder-pro.

Kwaipilot: KAT-Coder-Pro V1 accepts text and returns text. It has a 262,144-token context window.

It was released on November 10, 2025.

More models from Kwaipilot

  • KAT-Coder-Air V2.5
  • KAT-Coder-Pro V2.5
  • KAT-Coder-Pro V2

Frequently asked questions

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.

KAT-Coder-Pro V1 has a 262,144 token context window.

KAT-Coder-Air V2.5, KAT-Coder-Pro V2.5 and KAT-Coder-Pro V2 are other text models from Kwaipilot.

KAT-Coder-Pro V1 was released on November 10, 2025.