All AI models · LLM benchmarks · Methodology

Kwaipilot

KAT-Coder-Pro V1

Coding model for repository understanding, refactors, and agentic engineering tasks

Model facts

Context window
256K tokens
Maximum output
32K tokens
Cheapest paid input
$0.3 per 1M tokens
Cheapest paid output
$1.2 per 1M tokens
Open weights
no
Providers
2

Capabilities and modalities

reasoning, temperature control, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default28.9not measured94.7not measured

Observed price history

  • 2026-08-24: $0.3 input / $1.2 output per 1M tokens

API providers

  • Vercel AI Gateway — model id kwaipilot/kat-coder-pro-v1; $0.3 input / $1.2 output per 1M tokens; provider documentation
  • Arena — model id KAT-Coder-Pro-V1; not published input / not published output per 1M tokens; provider documentation