{"source":"BenchGecko","url":"https://benchgecko.ai/model/kat-coder-pro","as_of":"2026-03-27","license":"BenchGecko collected data (prices, provider offers, Gecko Tests) is CC BY 4.0 · https://creativecommons.org/licenses/by/4.0/. Benchmark scores belong to their original publishers (see sources) and are aggregated with attribution. Attribution required: \"Source: BenchGecko\" with a link.","attribution":"Source: BenchGecko · https://benchgecko.ai/model/kat-coder-pro","cite":"KAT-Coder-Pro V1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-03-27. https://benchgecko.ai/model/kat-coder-pro","slug":"kat-coder-pro","name":"KAT-Coder-Pro V1","provider":{"name":"kwaipilot","slug":"kwaipilot"},"model_type":"text","release_date":"2025-11-10","is_open_source":false,"status":"active","context_window":256000,"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. \n\nThe 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.","benchgecko_score":null,"avg_score":0,"list_price":{"input_usd_per_m":0.207,"output_usd_per_m":0.828,"source":"OpenRouter models API (checked daily)","as_of":"2026-10-05"},"pricing":{"input":0.207,"output":0.828},"providers":[],"cheapest_provider":null,"providers_source":null,"scores":[],"gecko_tests":null,"links":{"page":"https://benchgecko.ai/model/kat-coder-pro","json":"https://benchgecko.ai/api/v1/models/kat-coder-pro","price_history":"https://benchgecko.ai/api/v1/price-history/kat-coder-pro","provider_prices":null}}