Kwaipilot: KAT-Coder-Pro V1

Text input Text output
Author's Description

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.

Key Specifications
Cost
$$$
Context
256K
Released
Nov 09, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Tool Choice Temperature Structured Outputs Response Format Max Tokens Tools Frequency Penalty
Features

This model supports the following features:

Structured Outputs Response Format Tools
Performance Summary

Kwaipilot's KAT-Coder-Pro V1, created on November 9, 2025, is an advanced agentic coding model optimized for real-world software engineering tasks, achieving a 73.4% solve rate on SWE-Bench Verified. The model performs among the fastest models, ranking in the 65th percentile for speed, and offers competitive pricing, placing in the 66th percentile for cost-effectiveness. Notably, it demonstrates exceptional reliability with a 100% success rate across all benchmarks, indicating consistent and usable responses. Key strengths include strong performance in General Knowledge (99.0% accuracy), Ethics (99.0% accuracy), and Reasoning (84.0% accuracy, 73rd percentile). Its agentic capabilities are further supported by a solid 60.0% accuracy in Instruction Following. However, a notable weakness is its performance in Hallucinations, where it achieved only 82.0% accuracy (28th percentile), suggesting room for improvement in acknowledging uncertainty. While its Coding accuracy is 82.0%, its percentile ranking (47th) indicates it's an average performer in this specific benchmark compared to others.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.207
Completion $0.828
Input Cache Read $0.0414

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
StreamLake
StreamLake | kwaipilot/kat-coder-pro-v1 256K $0.207 / 1M tokens $0.828 / 1M tokens
AtlasCloud
AtlasCloud | kwaipilot/kat-coder-pro-v1 256K $0.207 / 1M tokens $0.828 / 1M tokens
Novita
Novita | kwaipilot/kat-coder-pro-v1 256K $0.207 / 1M tokens $0.828 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration