H Hvoy AI
Back to gateway directory
Site domain
packyapi.ai
Established
Not listed
Covered models
Fable 5 / Opus 4.8 / Opus 4.7 / Sonnet 5 / GPT 5.6 Sol / GPT 5.6 Terra / GPT 5.5 / GLM 5.2 / GPT Image 2 / Opus 4.6
Public records
71 public records
User feedback
22 up / 54 down

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

Site introduction

PackyCode 是一家可靠高效的 API 中转服务商,提供 Claude Code、Codex、Gemini 等多种服务的中转。 PackyCode 大约是24年底25年初开始活跃, 是国内比较早针对Claude Code进行优化的供应商. 这个站点与开源社区互动比较频繁, 站长在x上也非常活跃, 客服响应比较快. 随着发展, 这个站已经是很多中转站的上游供应商.

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

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

Price listing

Opus 4.7

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

Price listing

Sonnet 5

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

Price listing

GPT 5.6 Sol

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

Price listing

GPT 5.6 Terra

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

Price listing

GPT 5.5

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

Price listing

GLM 5.2

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

2 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
cc claude-fable-5 输入 ¥25 / 输出 ¥125 / 缓存 ¥2.5 / 写入 ¥31.25 +25%
claude-officially claude-fable-5 输入 ¥70 / 输出 ¥350 / 缓存 ¥7 / 写入 ¥87.5 0%

Opus 4.8

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
cc claude-opus-4-8 输入 ¥12.5 / 输出 ¥62.5 / 缓存 ¥1.25 / 写入 ¥15.63 +25%
claude-officially claude-opus-4-8 输入 ¥35 / 输出 ¥175 / 缓存 ¥3.5 / 写入 ¥43.75 0%

Opus 4.7

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
cc claude-opus-4-7 输入 ¥12.5 / 输出 ¥62.5 / 缓存 ¥1.25 / 写入 ¥15.63 +25%
claude-officially claude-opus-4-7 输入 ¥35 / 输出 ¥175 / 缓存 ¥3.5 / 写入 ¥43.75 0%

Sonnet 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
cc claude-sonnet-5 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥6.25 +25%
claude-officially claude-sonnet-5 输入 ¥14 / 输出 ¥70 / 缓存 ¥1.4 / 写入 ¥17.5 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
codex gpt-5.6-sol 输入 ¥2.5 / 输出 ¥15 / 缓存 ¥0.25 / 写入 ¥3.13 0%
azure-sale gpt-5.6-sol 输入 ¥12.5 / 输出 ¥75 / 缓存 ¥1.25 / 写入 ¥15.63 0%
azure-officially gpt-5.6-sol 输入 ¥25 / 输出 ¥150 / 缓存 ¥2.5 / 写入 ¥31.25 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
codex gpt-5.6-terra 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥1.25 0%
azure-sale gpt-5.6-terra 输入 ¥5 / 输出 ¥30 / 缓存 ¥0.5 / 写入 ¥6.25 0%
azure-officially gpt-5.6-terra 输入 ¥10 / 输出 ¥60 / 缓存 ¥1 / 写入 ¥12.5 0%

GPT 5.5

1 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
azure-officially gpt-5.5 输入 ¥25 / 输出 ¥150 / 缓存 ¥2.5 / 写入 ¥0 0%

GLM 5.2

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
glm-sale glm-5.2 输入 ¥8 / 输出 ¥28 / 缓存 ¥2 / 写入 ¥0 0%
zai-officially glm-5.2 输入 ¥8 / 输出 ¥28 / 缓存 ¥2 / 写入 ¥0 +11%

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
image gpt-image-2 ¥0.4 / 次 -

Opus 4.6

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
cc claude-opus-4-6 输入 ¥12.5 / 输出 ¥62.5 / 缓存 ¥1.25 / 写入 ¥15.63 +25%
claude-officially claude-opus-4-6 输入 ¥35 / 输出 ¥175 / 缓存 ¥3.5 / 写入 ¥43.75 0%

Site notices

CC-Sale 分组现已临时恢复供应 ,具体可持续时间 暂不明确 。

CC-Sale 分组现已临时恢复供应 ,具体可持续时间 暂不明确 。 建议有使用需求的用户合理安排调用计划,避免因供应再次收紧影响业务。后续如有进一步调整,将另行公告。 PackyAPI 团队

Codex 分组将于今日下午 3:00 起临时上调计费倍率至 0.8 , 后续恢复时间另行通知。

Codex 分组将于今日下午 3:00 起临时上调计费倍率至 0.8 , 后续恢复时间另行通知。如需继续使用, 请知悉最新费率, 以免影响计费。 感谢你的理解与支持! PackyAPI 团队

deepseek-officially 分组 已正式上线 deepseek-flash 模型,现已开放调用。

deepseek-officially 分组 已正式上线 deepseek-flash 模型,现已开放调用。 根据 DeepSeek 官方说明,旧模型名 deepseek-v4-flash 、 deepseek-v4-flash-vision-exp 仍可调用,但原对应模型已下线,相关请求将统一由 DeepSeek-V4.1-Flash 提供服务,并按 Flash 价格 计费。 建议将请求中的模型名称更新为 deepseek-flash。 如遇调用异常,请及时联系客服反馈。 PackyAPI 团队

各位用户:

各位用户: 根据 DeepSeek 官方价格调整,PackyAPI 将于 北京时间 2026 年 9 月 10 日 12:00 起同步调整 DeepSeek Flash 系列模型 价格。 调整后价格如下: 输入(缓存命中):0.02 元 / 百万 Token 输入(缓存未命中):1 元 / 百万 Token 输出:4 元 / 百万 Token 高峰时段价格为基础价格的 2 倍。 请用户根据实际需求合理安排使用。 感谢大家一直以来的支持与理解。 PackyAPI 团队

Image 分组 现新增 gpt-image-2.5-flare 与 gpt-image-2.5-sunburst 两款模型, 倍率 均为 5X , 即日起开放

Image 分组 现新增 gpt-image-2.5-flare 与 gpt-image-2.5-sunburst 两款模型, 倍率 均为 5X , 即日起开放使用。 欢迎前往 Image 分组调用体验。 PackyAPI 团队

User reviews

3.5 / 5 from 4 approved reviews

n*** Verified user
★★★★★

服了,整个白天都是高峰期无法使用

访问全是高峰期,最低必须充值五十,这个谁敢用啊

w***
★★☆☆☆

随意涨价,看中deepseek-v4-flash折扣比较高,充值了50(50元起充),使用一段时间后变成8折了,原来是2.5折。。。。

q***
★★★★★

不错 很稳很好用的经常买,希望多优化一些模型

z*** Verified user
★★☆☆☆

用一段时间就注水了,但是体验的时候模型还是很稳,便宜是便宜

用的aws-q分组,便宜是真便宜,但是模型检测用了一段时间之后就不知道给路由到什么模型去了

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.