FREE AI INDEX / 统一产品界面我的收藏提交资源 ↗

FreeLLM 免费 AI 资源索引FreeLLM Free AI Index / 资源详情Offer details

LongCat-2.5 Preview / 2.0 · API + open weightsLongCat-2.5 Preview / 2.0 · API + open weights

Meituan · API + open weightsLongCat

✓ 实测通过✓ Network verified国内外均可用China + global国内 228ms · 海外 578msChina 228ms · Global 578ms✓ 接口已验证 · 227ms✓ Endpoint verified · 227ms

这个资源提供什么What this offer provides

Official docs now list LongCat-2.5-Preview and LongCat-2.0 with OpenAI/Anthropic-compatible endpoints and 1M context. The FAQ requires sufficient account balance or a Token Resource Pack, so the API must not be advertised as durably free. LongCat-2.0 downloadable weights remain a separate free-access path.Official docs now list LongCat-2.5-Preview and LongCat-2.0 with OpenAI/Anthropic-compatible endpoints and 1M context. The FAQ requires sufficient account balance or a Token Resource Pack, so the API must not be advertised as durably free. LongCat-2.0 downloadable weights remain a separate free-access path.

关键信息Key details

免费方式Free method官方 API 需余额或 Token 资源包,未确认长期免费额度;LongCat-2.0 权重可免费下载,自备算力Paid/quota-backed official API plus downloadable LongCat-2.0 open weights
有效期ValidityAPI paid / quota-based · LongCat-2.0 weights openAPI paid / quota-based · LongCat-2.0 weights open
访问条件AccessAPI Email / phone;权重 GlobalAPI email / phone; weights global download path
最后核验Last checked2026-09-29

快速上手Quick start

通过 LongCat 官方 OpenAI/Anthropic 兼容 API 调用 LongCat-2.5-Preview 或 LongCat-2.0;LongCat-2.0 也可下载权重本地部署Follow the model-specific steps to register, create a key and connect the model.

✓

注册与接入步骤Registration and access steps

准备条件Prerequisites

  • LongCat 账号与 API Key
  • API 账户有足够余额或 Token 资源包;本地部署需自备硬件
  1. 在 LongCat 平台创建 API Key,并确认 Usage 页余额/资源包LongCat API Key, Usage
  2. 使用 OpenAI 或 Anthropic 兼容端点调用 LongCat-2.5-Preview;如需免费权重,下载 LongCat-2.0 本地部署OpenAI Anthropic LongCat-2.5-Preview; , LongCat-2.0
4

发送第一条请求Send first request

使用下方命令开始调用。Use the command below to make your first request.

可复制命令Copyable command
export LONGCAT_API_KEY="你的 Key"
curl --request POST https://api.longcat.chat/openai/v1/chat/completions --header "Authorization: Bearer $LONGCAT_API_KEY" --header 'Content-Type: application/json' --data '{"model":"LongCat-2.5-Preview","messages":[{"role":"user","content":"Hello"}],"max_tokens":1000}'

上下文窗口Context window

1M tokens1M tokens. 来源Source ↗

使用入口Access paths

入口Path用途Use免费状态Free status访问条件Access官方链接Official links
API 调用API
api
在线调用 LongCat-2.5-Preview / LongCat-2.0LongCat-2.5-Preview / LongCat-2.0官方文档未确认长期免费 API;需有余额或 Token 资源包API; TokenEmail / phoneEmail / phoneAPI docsAPI docs ↗ FAQFAQ ↗ Change logChange log ↗
下载权重Access path
open_weights
下载 LongCat-2.0 权重并在本地运行LongCat-2.0权重免费,算力不免费,GlobalGlobalOfficial GitHubOfficial GitHub ↗ Hugging FaceHugging Face ↗

详细操作步骤Detailed operation paths

每条路径都拆成前置条件、步骤、可复制命令和验证动作;免费条件仍以官方页面实时状态为准。curl 命令按 macOS / Linux shell 编写,Windows 用户可使用同页的 Python 或 Node.js 示例。Each path includes prerequisites, steps, copyable commands and a validation action; free terms still follow the provider's live official policy. The curl examples use a macOS/Linux shell; Windows users can run the Python or Node.js examples on this page.

LongCat API 调用

api

EndpointEndpoint
https://api.longcat.chat/openai/v1
认证Authentication
Authorization: Bearer API key

前置条件Prerequisites

  • 已注册 LongCat 平台LongCat
  • 已创建 API keyAPI key
  • 已确认账户可用额度与当前模型 IDID

操作步骤Steps

  1. 获取 API key

    从 LongCat 官方平台进入 API key 或开发者设置,创建密钥并保存为 LONGCAT_API_KEY 环境变量。

  2. 查看模型列表

    先访问官方模型接口,确认账户当前可见的模型 ID。

    可复制命令Copyable command
    export LONGCAT_API_KEY="你的 Key"
    curl https://api.longcat.chat/openai/v1/models -H "Authorization: Bearer $LONGCAT_API_KEY"

    预期结果Expected:返回 HTTP 200 和 data 模型列表。

  3. 发送聊天请求

    把 model 改为模型列表中的真实 ID,先用短文本验证。

    命令已在上方「快速上手」给出。The copyable command already appears in Quick start above.

    预期结果Expected:响应包含 choices[0].message.content。

验证动作Validation

GET /openai/v1/models 返回 HTTP 200,随后聊天接口返回 choices;额度和模型可用性以控制台为准。

官方来源Official sources

下载 LongCat-2.0 开源权重

download

前置条件Prerequisites

  • 已安装 Python 与 Hugging Face Hub CLIPython Hugging Face Hub CLI
  • 有足够磁盘和显存或 CPU 内存CPU
  • 已阅读模型仓库许可证See official terms

操作步骤Steps

  1. 阅读官方仓库

    先确认模型卡、许可证、硬件建议和推理方式。

    操作Action:打开 https://github.com/meituan-longcat/LongCat-2.0

  2. 安装下载工具

    在独立虚拟环境中安装 Hugging Face Hub。

    可复制命令Copyable command
    python -m pip install -U huggingface_hub
  3. 下载权重

    将权重保存到明确的本地目录,避免覆盖已有模型。

    可复制命令Copyable command
    huggingface-cli download meituan-longcat/LongCat-2.0 --local-dir ./LongCat-2.0
  4. 按仓库说明启动

    使用仓库提供的推理命令,并根据实际显存调整量化或并行参数。

验证动作Validation

下载目录包含模型配置与权重文件,并能按官方仓库示例完成一次本地推理。

官方来源Official sources

官方来源Official sources

Official LongCat docs list LongCat-2.5-Preview and LongCat-2.0, 1M context and OpenAI/Anthropic-compatible APIs. The official FAQ tells users to ensure the account has sufficient balance and states Token Resource Packs support both models; no durable free API quota is documented.Official LongCat docs list LongCat-2.5-Preview and LongCat-2.0, 1M context and OpenAI/Anthropic-compatible APIs. The official FAQ tells users to ensure the account has sufficient balance and states Token Resource Packs support both models; no durable free API quota is documented.

相关资源Related resources