Meituan Models

2 modelsGeneral models from $0.7746/M inputUp to 1M context

Usage

Last 30 days · 2026-10-23 to 2026-11-21

Tokens

145M

Requests

884

Models in use

2 of 2

Tokens per day, stacked by model

041.9M83.9M10-2310-3011-0611-1311-202026-10-23 — 319,980 tokens longcat-2.0: 319,9802026-10-24 — 259,195 tokens longcat-2.0: 259,1952026-10-25 — 160,065 tokens longcat-2.0: 160,0652026-10-26 — 417,675 tokens longcat-2.0: 417,6752026-10-27 — 10,430 tokens longcat-2.0: 10,4302026-10-28 — 5,185,420 tokens longcat-2.0: 5,185,4202026-10-29 — 928,870 tokens longcat-2.0: 928,8702026-10-30 — 4,235 tokens longcat-2.0: 4,2352026-10-31 — 1,625 tokens longcat-2.0: 1,6252026-11-01 — 1,700 tokens longcat-2.0: 1,7002026-11-02 — 4,466,920 tokens longcat-2.0: 4,466,9202026-11-03 — 18,900 tokens longcat-2.0: 18,9002026-11-04 — 2,145 tokens longcat-2.0: 2,1452026-11-05 — 10,170 tokens longcat-2.0: 10,1702026-11-06 — 17,000 tokens longcat-2.0: 17,0002026-11-07 — 36,450 tokens longcat-2.0: 36,4502026-11-08 — 63,885 tokens longcat-2.0: 63,8852026-11-09 — 9,430 tokens longcat-2.0: 9,4302026-11-10 — 1,131,955 tokens longcat-2.0: 1,131,9552026-11-11 — 2,635 tokens longcat-2.0: 2,6352026-11-12 — 6,230 tokens longcat-2.0: 6,2302026-11-13 — 314,815 tokens longcat-2.0: 314,8152026-11-14 — 46,774,935 tokens longcat-2.0: 46,774,9352026-11-15 — 1,785 tokens longcat-2.0: 1,7852026-11-16 — 199,225 tokens longcat-2.0: 199,2252026-11-17 — 452,195 tokens longcat-2.0: 452,1952026-11-18 — 83,898,625 tokens longcat-2.0: 83,898,6252026-11-19 — 33,855 tokens longcat-2.0: 33,8552026-11-20 — 1,680 tokens longcat-2.0: 1,6802026-11-21 — 2,405 tokens longcat-2.0: 2,405

Which models that traffic went to

  1. Longcat 2.0100.0%145M

Share of 145M tokens. 1 models with traffic report no token counts and cannot be ranked here, including LongCat-Flash-Chat — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 2 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 2 Meituan Models

Open in model list
Meituan models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
longcat-2.0Takes text, returns text.1M131K$0.7746$3.0984/M$0.0155/M38 tok/s6.07 s
LongCat-Flash-ChatTakes , returns text.——$0.14$0.7/M———

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Meituan on AIHubMix

Which Meituan model should I start with?

longcat-2.0 at $0.7746/M input — the cheapest entry here that declares tool calling, and it carries a 1M context. Move up to LongCat-Flash-Chat when answer quality matters more than cost.

Which of these models reason before answering?

1 of the 2 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example longcat-2.0 bills cache hits at 2% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate Meituan account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Start calling Meituan in one line

One key, one endpoint, 984 models across 49 model authors.