H Hvoy AI
Back to gateway directory
Site domain
api.vllmproxy.com
Established
2026-04-24
Covered models
Fable 5 / Opus 4.8 / Opus 4.7 / Sonnet 5 / GPT 5.6 Sol / GPT 5.6 Terra / GPT 5.5 / GPT Image 2 / Opus 4.6
Public records
56 public records
User feedback
0 up / 0 down

Site descriptions, notices, and reviews are shown in the language in which they were submitted.

Site introduction

本平台是面向开发者、团队与企业用户的高可用 AI API 中转与聚合服务,致力于提供稳定、低延迟、高性价比的大模型调用能力。平台支持 GPT、Claude、Gemini 等多种主流 AI 模型,通过统一 API 接口即可快速接入,适用于 AI 应用开发、Agent 构建、产品原型验证、自动化工具以及企业内部系统集成等多种场景。 平台采用稳定资源池与多节点架构设计,结合 Cloudflare CDN 加速分发,有效降低国内访问延迟,提升接口响应速度与调用稳定性。支持高并发请求与多线路调度,能够更好地保障业务连续运行,为开发者提供长期稳定、可靠可用的 API 服务体验。 同时,平台提供多域名容灾与灵活切换机制,持续优化线路质量与模型支持能力。客服长期在线,问题快速响应,接口异常及时处理,并坚持按量计费、价格透明、无隐形收费,帮助个人开发者、团队和企业以更低成本稳定接入 AI 能力。

Model coverage summary

Price listing

Fable 5

2 public records are listed; open the full page to review details as needed.

Price listing

Opus 4.8

4 public records are listed; open the full page to review details as needed.

Price listing

Opus 4.7

4 public records are listed; open the full page to review details as needed.

Price listing

Sonnet 5

4 public records are listed; open the full page to review details as needed.

Price listing

GPT 5.6 Sol

4 public records are listed; open the full page to review details as needed.

Price listing

GPT 5.6 Terra

4 public records are listed; open the full page to review details as needed.

Price listing

GPT 5.5

2 public records are listed; open the full page to review details as needed.

Price listing

GPT Image 2

1 public records are listed; open the full page to review details as needed.

Price listing

Opus 4.6

4 public records are listed; open the full page to review details as needed.

Public model pricing

Current public prices are shown by model and channel. Token prices use CNY per 1M tokens unless another billing unit is shown.

Fable 5

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
ccmax 20x claude-fable-5 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥15 0%
ccmax 可外接 claude-fable-5 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥15 0%

Opus 4.8

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
kiro_带缓存 claude-opus-4-8 输入 ¥0.9 / 输出 ¥4.5 / 缓存 ¥0.09 / 写入 ¥1.13 0%
kiro正价号池 claude-opus-4-8 输入 ¥1.25 / 输出 ¥6.25 / 缓存 ¥0.125 / 写入 ¥1.56 0%
ccmax 20x claude-opus-4-8 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 0%

Opus 4.7

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
kiro_带缓存 claude-opus-4-7 输入 ¥0.9 / 输出 ¥4.5 / 缓存 ¥0.09 / 写入 ¥1.13 0%
kiro正价号池 claude-opus-4-7 输入 ¥1.25 / 输出 ¥6.25 / 缓存 ¥0.125 / 写入 ¥1.56 0%
ccmax 20x claude-opus-4-7 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 0%

Sonnet 5

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
kiro_带缓存 claude-sonnet-5 输入 ¥0.54 / 输出 ¥2.7 / 缓存 ¥0.054 / 写入 ¥0.675 0%
kiro正价号池 claude-sonnet-5 输入 ¥0.75 / 输出 ¥3.75 / 缓存 ¥0.075 / 写入 ¥0.9375 0%
ccmax 20x claude-sonnet-5 输入 ¥3.6 / 输出 ¥18 / 缓存 ¥0.36 / 写入 ¥4.5 0%

GPT 5.6 Sol

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
default gpt-5.6-sol 输入 ¥0.45 / 输出 ¥2.7 / 缓存 ¥0.045 / 写入 ¥0.5625 0%
gpt_plus号池 gpt-5.6-sol 输入 ¥0.45 / 输出 ¥2.7 / 缓存 ¥0.045 / 写入 ¥0.5625 0%
gpt_pro gpt-5.6-sol 输入 ¥1.1 / 输出 ¥6.6 / 缓存 ¥0.11 / 写入 ¥1.38 0%

GPT 5.6 Terra

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
default gpt-5.6-terra 输入 ¥0.18 / 输出 ¥1.08 / 缓存 ¥0.018 / 写入 ¥0.2813 0%
gpt_plus号池 gpt-5.6-terra 输入 ¥0.18 / 输出 ¥1.08 / 缓存 ¥0.018 / 写入 ¥0.2813 0%
gpt_pro gpt-5.6-terra 输入 ¥0.44 / 输出 ¥2.64 / 缓存 ¥0.044 / 写入 ¥0.6875 0%

GPT 5.5

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
gpt_pro gpt-5.5 输入 ¥1.1 / 输出 ¥6.6 / 缓存 ¥0.11 / 写入 ¥1.1 0%
gpt_pro破限分组 gpt-5.5 输入 ¥1.4 / 输出 ¥8.4 / 缓存 ¥0.14 / 写入 ¥1.4 0%

GPT Image 2

1 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
生图模型 gpt-image-2 ¥0.02 / 次 -

Opus 4.6

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
kiro_带缓存 claude-opus-4-6 输入 ¥0.9 / 输出 ¥4.5 / 缓存 ¥0.09 / 写入 ¥1.13 0%
kiro正价号池 claude-opus-4-6 输入 ¥1.25 / 输出 ¥6.25 / 缓存 ¥0.125 / 写入 ¥1.56 0%
ccmax 20x claude-opus-4-6 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 0%

Site notices

📢 社群公告

📢 社群公告 本服务不再为中国大陆用户提供服务。 为了方便大家交流、反馈问题和获取最新通知,欢迎加入我们的官方交流群。 加入方式 qq群 1101035836 Telegram 群 链接: https://t.me/yuntongz 温馨提示 进群后请遵守群规,文明交流。 如遇使用问题、充值问题、接口问题或模型调用异常,可在群内联系管理员处理。

因服务器压力较大,为了给各位大佬更好的体验。

因服务器压力较大,为了给各位大佬更好的体验。8日早上6-8点升级服务器。

本平台仅供内部技术研究、接口测试及系统验证使用。

本平台仅供内部技术研究、接口测试及系统验证使用。 仅限授权人员访问 禁止账号共享、转借、出租或转售 禁止接口转售及任何商业化用途 系统将记录访问日志、调用记录及异常行为用于安全审计 对于接口滥用、异常请求、恶意测试、违规内容生成或泄露平台信息等行为,平台有权限制或永久封禁相关账号。 非授权访问区域禁止访问 Internal Use Only

各位大佬,最新渠道更新如下

各位大佬,最新渠道更新如下 1. 新上claude多个渠道 2. plus号池全部分组价格为0.1倍率 3. gemini模型上架 4. gpt pro降价为0.3,vip分组降低为0.25

5/9/2026 18:00:00实行

5/9/2026 18:00:00实行 由于目前 GPT Pro 号池均为正价开通,整体成本大幅上涨,之前一直是亏本给大家提供服务。为了保证服务能够长期稳定运行,现对部分价格和权益做如下调整: 1. GPT Pro 使用倍率调整为 0.35 2. 新增订阅分组:18.8 元 订阅后赠送 8.8 元余额 订阅vip gpt pro分组享受0.33倍率 定于vip cc满血特价享受0.4倍率

User reviews

5.0 / 5 from 2 approved reviews

q*** Verified user
★★★★★

很好用,体验比预期更省心

模型都是很超前的,体验下来没出过什么问题,消耗也很低,使用过程中稳定性挺好,没有遇到明显问题,性价比也可以。客服/售后响应也比较及时,有问题能处理,整体体验挺省心

n***
★★★★★

相当好用,找了四五家,就这家的最好用已经用了好几个月了

值得推荐,相当好用,找了四五家,就这家的最好用最划算。有什么问题站长第一时间帮助处理,刚开始不会用还帮忙远程。已经用了好几个月了,相当良心好用,赞!

How to read this data

Uptime is the share of recent probes where the service was available; a higher value generally indicates better stability.

Model consistency uses model pass results to show whether the endpoint behaves like the target model.

Pricing and latency come from public monitoring data and are intended for side-by-side gateway comparison.

Data is provided for reference. Third-party gateways may experience outages or balance loss, so test first and add only a small balance when needed.