Skip to content
KwaiPilot

Kat Coder Pro V2.5

Kat Coder Pro V2.5 is the flagship of KwaiPilot's KAT-Coder V2.5 generation. It scores 65.2 on SWE-Bench Pro and 94.9 on PinchBench, with a context window of 256K tokens and output up to 80K tokens. Your use is subject to KwaiPilot's Terms & Privacy Policies.

ReasoningTool UseImplicit CachingVision (Image)
Use with AI GatewayView docs
import { streamText } from 'ai'


const result = streamText({
  model: 'kwaipilot/kat-coder-pro-v2.5',
  prompt: 'Why is the sky blue?'
})
Read docs
OverviewAPIAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

Frequently Asked Questions

  • What is Kat Coder Pro V2.5's SWE-Bench Pro score?

    65.2. That places Kat Coder Pro V2.5 second in KwaiPilot's published comparison, behind Opus 4.8 at 69.2. SWE-Bench Pro measures whether an agent can resolve repository-level engineering tasks end to end.

  • How does Kat Coder Pro V2.5 differ from KAT-Coder Air V2.5?

    Kat Coder Pro V2.5 posts a higher SWE-bench figure in KwaiPilot's model comparison, 65.2% against 42.4% for kat-coder-air-v2.5. Both share a context window of 256K tokens, output up to 80K tokens, context caching, function calling, and MCP support. KwaiPilot positions Air as the fast-response option for high-volume agent workloads.

  • What is PinchBench and how did Kat Coder Pro V2.5 score?

    PinchBench measures agentic tool use. Kat Coder Pro V2.5 records 94.9, the best result in KwaiPilot's published comparison, ahead of Opus 4.8 at 93.5.

  • What is the context window and maximum output for Kat Coder Pro V2.5?

    256K tokens of context and up to 80K tokens of output per request.

  • Does Kat Coder Pro V2.5 support tool calling and MCP?

    Yes. KwaiPilot lists streaming output, context caching, MCP (Model Context Protocol), and function calling for Kat Coder Pro V2.5.

  • Which programming languages does Kat Coder Pro V2.5 cover?

    KwaiPilot lists more than 20 mainstream programming languages, including C, C++, Java, and Python.

  • How do I call Kat Coder Pro V2.5 through AI Gateway?

    Set the model identifier to kwaipilot/kat-coder-pro-v2.5 and use your AI Gateway API key. Kat Coder Pro V2.5 works through the AI SDK as well as the Chat Completions API and the other request formats AI Gateway accepts.

  • What does Kat Coder Pro V2.5 cost?

    Current rates appear in the pricing panel on this page, including cached input reads at $0.15 per million tokens. AI Gateway reflects provider pricing, and StreamLake serves Kat Coder Pro V2.5.

  • When was Kat Coder Pro V2.5 released?

    July 10, 2026, alongside kat-coder-air-v2.5.

  • Is Zero Data Retention available for Kat Coder Pro V2.5?

    Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.