Meituan: LongCat-2.5Official docs

Meituan: LongCat-2.5

byMeituan
Official docs

LongCat-2.5 is a reasoning model from Meituan released on Nov 2, 2026. It reads text and images and writes text, with a 1M token context window and up to 262K tokens per reply.

Show more

It costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input bills at $0.006, 98% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

3 providers serve it, including Vercel AI Gateway, Kilo Gateway and Kenari.

Modalities
In / out price
$0.30 / $1.20 per 1M
Context
1M
Max output
262K
Released
Nov 2, 2026
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

LongCat-2.5 pricing

USD, as listed on Nov 17, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Cached input (read)$0.006 / 1M tokens

LongCat-2.5 providers

3 providers serve it, including Vercel AI Gateway, Kilo Gateway and Kenari. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Vercel AI Gateway$0.30$1.20$0.0061.05M131K
Kilo Gateway$0.30$1.20$0.0061.05M131K
Kenarin/an/an/a1M262K

What LongCat-2.5 costs per month

Pick a workload close to yours or type your own volumes.

LongCat-2.5 per month
$21.87
Without caching
$35.10
Per request
$0.0007

Supported request parameters

What you can set when you call LongCat-2.5 through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning

Alternatives to LongCat-2.5

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text and images. Tool calling, structured output, reasoning. Served by 90 providers.

    by deepseekSep 10, 20261.05M context$0.30/M input tokens$1.20/M output tokens90 providers

  • Index 29.2

    Reads text, images and video. Tool calling, structured output, reasoning. Served by 50 providers.

    by minimaxJun 1, 20261M context$0.30/M input tokens$1.20/M output tokens50 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 51 providers.

    by openaiJul 9, 2026$0.20/M input tokens$1.20/M output tokens51 providers

  • Reads text and images. Tool calling, structured output, reasoning.

    by fireworksOct 17, 2026$0.30/M input tokens$1.20/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 17, 2026$0.30/M input tokens$1.20/M output tokens

  • Reads text and images. Tool calling, structured output, reasoning.

    by baiduOct 17, 2026$0.28/M input tokens$1.13/M output tokens

More from Meituan

All Meituan models

LongCat-2.5 questions

How much does the LongCat-2.5 API cost?

$0.30 per million input tokens and $1.20 per million output tokens, with cached input at $0.006. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of LongCat-2.5?

1,000,000 tokens of input, and it can write up to 262,144 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve LongCat-2.5?

3 providers serve it, including Vercel AI Gateway, Kilo Gateway and Kenari. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does LongCat-2.5 support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is LongCat-2.5 open source?

No. Meituan serves it through an API only, so you cannot download the weights or host it yourself.

When was LongCat-2.5 released?

Nov 2, 2026.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 17, 2026. The summary is written from these facts.