H Hvoy AI
Back to gateway directory
Site domain
buzzai.cc
Established
Not listed
Covered models
GPT 5.6 Sol / GPT 5.5 / Opus 5 / Claude Fable 5 / GPT Image 2 / Claude Opus 4.8 / GPT 5.6 Terra / Kimi K3 / Claude Opus 4.6 / Claude Sonnet 5 / Claude Opus 4.7 / Claude Sonnet 4.6 / GPT 5.4
Public records
32 public records
User feedback
2 up / 1 down

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

Site introduction

BUZZ AI 提供 Claude API 中转网关服务,支持 Claude Opus 4.6、Sonnet 4.6、Haiku 4.5 全系列模型。透明转发、按量计费、原生 Prompt Cache 支持、零数据留存,为中国开发者提供稳定可靠的 Claude API 接入方案。

Model coverage summary

Price listing

GPT 5.6 Sol

2 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

Opus 5

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

Price listing

Claude Fable 5

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

Price listing

GPT Image 2

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

Price listing

Claude Opus 4.8

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

Price listing

GPT 5.6 Terra

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

Price listing

Kimi K3

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

Price listing

Claude Opus 4.6

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

Price listing

Claude Sonnet 5

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

Price listing

Claude Opus 4.7

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

Price listing

Claude Sonnet 4.6

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

Price listing

GPT 5.4

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.

GPT 5.6 Sol

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Codex-Plus gpt-5.6-sol 输入 ¥0.2 / 输出 ¥1.6 / 缓存 ¥0.02 / 写入 ¥0.25 0%
Codex-Pro gpt-5.6-sol 输入 ¥0.3 / 输出 ¥2.4 / 缓存 ¥0.03 / 写入 ¥0.375 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
Codex-Plus gpt-5.5 输入 ¥0.2 / 输出 ¥1.2 / 缓存 ¥0.02 / 写入 ¥0.25 0%
Codex-Pro gpt-5.5 输入 ¥0.3 / 输出 ¥1.8 / 缓存 ¥0.03 / 写入 ¥0.375 0%

Opus 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
aws claude-opus-5 输入 ¥0.2 / 输出 ¥1 / 缓存 ¥0.02 / 写入 ¥0 -50%
Corp Max claude-opus-5 输入 ¥1.15 / 输出 ¥5.75 / 缓存 ¥0.115 / 写入 ¥0 +21%
max claude-opus-5 输入 ¥1.5 / 输出 ¥7.5 / 缓存 ¥0.15 / 写入 ¥0 0%

Claude 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
Corp Max claude-fable-5 输入 ¥2.3 / 输出 ¥11.5 / 缓存 ¥0.23 / 写入 ¥2.88 +21%
max claude-fable-5 输入 ¥3 / 输出 ¥15 / 缓存 ¥0.3 / 写入 ¥3.75 0%

GPT Image 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
Codex-Plus gpt-image-2 输入 ¥0.2 / 输出 ¥1.2 / 缓存 ¥0.05 / 写入 ¥0 0%
Codex-Pro gpt-image-2 输入 ¥0.3 / 输出 ¥1.8 / 缓存 ¥0.075 / 写入 ¥0 0%

Claude 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
aws claude-opus-4-8 输入 ¥0.2 / 输出 ¥1 / 缓存 ¥0.02 / 写入 ¥0.25 -50%
Corp Max claude-opus-4-8 输入 ¥1.15 / 输出 ¥5.75 / 缓存 ¥0.115 / 写入 ¥1.44 +21%
max claude-opus-4-8 输入 ¥1.5 / 输出 ¥7.5 / 缓存 ¥0.15 / 写入 ¥1.88 0%

GPT 5.6 Terra

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Codex-Plus gpt-5.6-terra 输入 ¥0.08 / 输出 ¥0.64 / 缓存 ¥0.008 / 写入 ¥0.05 -20%
Codex-Pro gpt-5.6-terra 输入 ¥0.12 / 输出 ¥0.96 / 缓存 ¥0.012 / 写入 ¥0.075 -20%

Kimi K3

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Kimi-OSS kimi-k3 输入 ¥2.1 / 输出 ¥10.5 / 缓存 ¥0.21 / 写入 ¥0 0%
Moonshot kimi-k3 输入 ¥3 / 输出 ¥15 / 缓存 ¥0.3 / 写入 ¥0 0%

Claude 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
aws claude-opus-4-6 输入 ¥0.2 / 输出 ¥1 / 缓存 ¥0.02 / 写入 ¥0.25 -50%
Corp Max claude-opus-4-6 输入 ¥1.15 / 输出 ¥5.75 / 缓存 ¥0.115 / 写入 ¥1.44 +21%
max claude-opus-4-6 输入 ¥1.5 / 输出 ¥7.5 / 缓存 ¥0.15 / 写入 ¥1.88 0%

Claude 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
aws claude-sonnet-5 输入 ¥0.08 / 输出 ¥0.4 / 缓存 ¥0.008 / 写入 ¥0.1 -50%
Corp Max claude-sonnet-5 输入 ¥0.46 / 输出 ¥2.3 / 缓存 ¥0.046 / 写入 ¥0.575 +21%
max claude-sonnet-5 输入 ¥0.6 / 输出 ¥3 / 缓存 ¥0.06 / 写入 ¥0.75 0%

Claude 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
aws claude-opus-4-7 输入 ¥0.2 / 输出 ¥1 / 缓存 ¥0.02 / 写入 ¥0.25 -50%
Corp Max claude-opus-4-7 输入 ¥1.15 / 输出 ¥5.75 / 缓存 ¥0.115 / 写入 ¥1.44 +21%
max claude-opus-4-7 输入 ¥1.5 / 输出 ¥7.5 / 缓存 ¥0.15 / 写入 ¥1.88 0%

Claude Sonnet 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
aws claude-sonnet-4-6 输入 ¥0.12 / 输出 ¥0.6 / 缓存 ¥0.012 / 写入 ¥0 -50%
Corp Max claude-sonnet-4-6 输入 ¥0.69 / 输出 ¥3.45 / 缓存 ¥0.069 / 写入 ¥0 +21%
max claude-sonnet-4-6 输入 ¥0.9 / 输出 ¥4.5 / 缓存 ¥0.09 / 写入 ¥0 0%

GPT 5.4

2 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Codex-Plus gpt-5.4 输入 ¥0.1 / 输出 ¥0.6 / 缓存 ¥0.01 / 写入 ¥0.125 0%
Codex-Pro gpt-5.4 输入 ¥0.15 / 输出 ¥0.9 / 缓存 ¥0.015 / 写入 ¥0.1875 0%

Site notices

受上游新方案的技术影响,AWS Lite 分组的缓存命中率出现小幅下降。

受上游新方案的技术影响,AWS Lite 分组的缓存命中率出现小幅下降。 为此我们已将该分组倍率由 0.08 下调至 0.06,即时生效。 调整仅对生效后新产生的用量生效,此前的用量仍按原倍率计费。 每笔请求的实际扣费明细可在「用量日志」中查看。 感谢你一直以来的支持。 Due to a technical change in our upstream provider's new plan, the cache hit rate for the AWS Lite group has decreased slightly. To offset this, we have lowered the group rate from 0.08 to 0.06, effective immediately. The new rate applies only to usage generated after it takes effect; earlier usage is billed at the previous rate. Per-request billing details remain available in your usage logs. Thank you for your continued support. 受上游新方案的技術影響,AWS Lite 分組的快取命中率出現小幅下降。 為此我們已將該分組倍率由 0.08 下調至 0.06,即時生效。 調整僅對生效後新產生的用量生效,此前的用量仍按原倍率計費。 每筆請求的實際扣費明細可在「用量日誌」中查看。 感謝你一直以來的支持。

Corp Max 分组价格将于 2026 年 8 月 4 日起调整,倍率由 0.19 调整为 0.23。

Corp Max 分组价格将于 2026 年 8 月 4 日起调整,倍率由 0.19 调整为 0.23。 调整于生效时间后对新产生的用量生效,此前的用量仍按原倍率计费。 账户余额金额不变,生效后同等用量的扣费相应提高。 每笔请求的实际扣费明细可在「用量日志」中查看。 感谢你一直以来的支持。 Pricing for the Corp Max group will be adjusted on August 4, 2026, with the rate changing from 0.19 to 0.23. The new rate applies to usage generated after the effective time; earlier usage is billed at the previous rate. Your balance amount is unchanged; after the change, the same usage will consume proportionally more of it. Per-request billing details remain available in your usage logs. Thank you for your continued support. Corp Max 分組價格將於 2026 年 8 月 4 日起調整,倍率由 0.19 調整為 0.23。 調整於生效時間後對新產生的用量生效,此前的用量仍按原倍率計費。 帳戶餘額金額不變,生效後同等用量的扣費相應提高。 每筆請求的實際扣費明細可在「用量日誌」中查看。 感謝你一直以來的支持。

控制台新增「实验功能」,可直接在网页上生成和编辑图片:支持参考图、批量出图,历史记录只保存在你自己的浏览器里。

控制台新增「实验功能」,可直接在网页上生成和编辑图片:支持参考图、批量出图,历史记录只保存在你自己的浏览器里。按 token 实际用量从余额扣费。欢迎向我们反馈建议与想法。 A new Experiments section is live in the console: generate and edit images right in the browser, with reference images and batch output. History stays in your own browser. Billed on actual token usage. Feel free to send us your feedback and suggestions. 控制台新增「實驗功能」,可直接在網頁上生成和編輯圖片:支援參考圖、批量出圖,歷史記錄只保存在你自己的瀏覽器裡。按 token 實際用量從餘額扣費。歡迎向我們回饋建議與想法。

新增 API 接入端点 api.buzzgw.com,与 api.buzzai.cc 并行提供服务,互为冗余。

新增 API 接入端点 api.buzzgw.com,与 api.buzzai.cc 并行提供服务,互为冗余。两个端点后端为同一套服务:同一账号、同一余额、同一 API 密钥。可在接入教程页对端点实时测速后选用。 A second API endpoint, api.buzzgw.com, is now live alongside api.buzzai.cc as mutual redundancy. Both are backed by the same service: same account, same balance, same API key. Measure latency on the integration guide page and pick either. 新增 API 接入端點 api.buzzgw.com,與 api.buzzai.cc 並行提供服務,互為冗餘。兩個端點後端為同一套服務:同一帳號、同一餘額、同一 API 金鑰。可在接入教程頁對端點即時測速後選用。

我们对部分 GPT 模型供给进行调整,同时新增性价比更高的 Codex Plus 套餐分组。

我们对部分 GPT 模型供给进行调整,同时新增性价比更高的 Codex Plus 套餐分组。 We have adjusted the supply of several GPT models and added the more cost-effective Codex Plus group. 我們對部分 GPT 模型供給進行調整,同時新增性價比更高的 Codex Plus 套餐分組。

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.