LongCat-2.5-Preview

MeituanMCP Tool CallReasoning
meituan/longcat-2.5-previewClosed API

Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window

Benchmark Pricing$0.75 / 1M in$2.95 / 1M out$0.01 cache read
Context: 1,000,000 tokens•Max Output: 131,072 tokens•Released: 2026-09-25

TECHNICAL SPECIFICATIONS

Context Window1,000,0001M tokens
Max Output131,072131.1K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVision
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ LongCat-2.5-Preview natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,000,000 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

API CALL INVOCATION EXAMPLE

// Example: Calling LongCat-2.5-Preview via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MEITUAN_API_KEY,
});

const response = await client.chat.completions.create({
  model: "meituan/longcat-2.5-preview",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

5 providers
NanoGPTlongcat-2.5-preview
$0.75 / $2.95$0.01 cache
OpenCode Golongcat-2.5-preview-free
$0.00 / $0.00$0.00 cache
Vercel AI Gatewaymeituan/longcat-2.5-preview
$0.30 / $1.20$0.01 cache
OpenCodelongcat-2.5-preview-free
$0.00 / $0.00$0.00 cache
LongCatLongCat-2.5-Preview
$0.30 / $1.20$0.01 cache

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.01 / 1M tokens, saving up to 98% on repetitive MCP tool definitions and system instructions.

MODEL RESOURCES