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.
View API reference- Input and output price
- Input $0.74, Output $2.96, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'kwaipilot/kat-coder-pro-v2.5', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Kat Coder Pro V2.5 by KwaiPilot. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Kat Coder Pro V2.5
Kat Coder Pro V2.5
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Kat Coder Pro V2.5 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Kat Coder Pro V2.5 request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. kwaipilot/kat-coder-pro-v2.5. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Kat Coder Pro V2.5 supports up to 80,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 256K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['streamlake'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'kwaipilot/kat-coder-pro-v2.5', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by KwaiPilot
| Model |
|---|
| 256K | $0.15/M | $0.60/M | Read$0.03/M | — | +1 |  | 07/10/2026 | |||||||
| 256K | $0.30/M | $1.20/M | Read$0.06/M | — | | 03/27/2026 | ||||||||
| 256K | $0.30/M | $1.20/M | Read$0.06/M | — |  | 11/09/2025 |
Copy link to headingAbout Kat Coder Pro V2.5
Kat Coder Pro V2.5 is the flagship model in KwaiPilot's KAT-Coder V2.5 generation, released July 10, 2026. A task starts from a natural-language issue and ends with a verified change. Kat Coder Pro V2.5 locates the relevant code across files, follows the repository's existing conventions, edits, and runs tests to confirm the change holds.
On SWE-Bench Pro, which measures repository-level software engineering, Kat Coder Pro V2.5 scores 65.2 and ranks second in KwaiPilot's published comparison, behind Opus 4.8 at 69.2. On PinchBench, an agentic tool-use benchmark, Kat Coder Pro V2.5 records 94.9, the top result in that comparison. It also scores 53.1 on KAT Code Bench, 60.7 on Terminal-Bench 2.1, and 50.3 on SciCode. Every model in that comparison ran under the same Claude Code harness, tool set, context budget, and decoding configuration.
Kat Coder Pro V2.5 supports streaming output, context caching, function calling, and MCP (Model Context Protocol), and KwaiPilot lists coverage of more than 20 mainstream programming languages including C, C++, Java, and Python. Cached input reads bill at $0.15 per million tokens, which matters for agent loops that resend the same repository context turn after turn. Route requests through AI Gateway to reach Kat Coder Pro V2.5 via StreamLake. Product details sit at .
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Kat Coder Pro V2.5 is the higher-capability half of the KAT-Coder V2.5 pair.
kat-coder-air-v2.5shares the same context window, output ceiling, and tool surface, and KwaiPilot publishes a lower SWE-bench figure for it. Compare the two against your own task mix before you commit. - Configuration: Agent sessions accumulate context quickly. The window of 256K tokens covers large multi-file work, but caching repeated context is what keeps per-turn cost predictable once a session runs long. Check the pricing panel on this page for current input, output, and cached read rates.
- Configuration: Benchmark numbers here come from KwaiPilot's own evaluation under a fixed harness. Treat them as a starting point and measure resolution rate on your repositories before you route production traffic.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Kat Coder Pro V2.5
Best for
- Autonomous Issue Resolution: Locate, edit, and verify changes inside a real repository
- Long-Horizon Engineering: Tasks spanning many files and dozens of tool calls per session
- MCP Agent Harnesses: Function calling and MCP support fit existing agent tooling
- Large Repository Sessions: A window of 256K tokens holds multi-file diffs and session history
- Cached Agent Loops: Context caching keeps resent repository context affordable
Consider alternatives when
- Air Tier Suffices:
kat-coder-air-v2.5shares the context window and output ceiling at lower cost - Multimodal Input Needed: Screenshots and diagrams require a model that accepts image input
- Terminal and Scientific Coding: Scores of 60.7 on Terminal-Bench 2.1 and 50.3 on SciCode trail the coding results
- General-Purpose Work: Writing and open-ended analysis sit outside a coding model's scope
Copy link to headingConclusion
Kat Coder Pro V2.5 is KwaiPilot's strongest KAT-Coder release for repository-level work, with 65.2 on SWE-Bench Pro and the top PinchBench result in its published comparison. Pair it with kat-coder-air-v2.5 on routine tasks and route both through AI Gateway so switching tiers is a model identifier change.
Copy link to headingFrequently 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-v2.5and 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.