Site descriptions, notices, and reviews are shown in the language in which they were submitted.
Aivoza 是一家可靠高效的 API 中转服务商，提供以Codex 为主 Claude Code、Grok、DeepSeek等多种服务的中转。 Aivoza 26年 5 月份开始活跃，也收获一些忠实比较认可站点的用户。 这个站点与开源社区互动比较频繁，站长在TG,QQ上也非常活跃，反馈响应比较快。 依旧相信美好的事情即将发生
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
3 public records are listed; open the full page to review details as needed.
Current public prices are shown by model and channel. Token prices use CNY per 1M tokens unless another billing unit is shown.
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 「Plus」OpenAI | gpt-5.6-sol | 输入 ¥0.8 / 输出 ¥4.8 / 缓存 ¥0.1 / 写入 ¥1 | 0% | — | — | — |
| 「Pro」OpenAI | gpt-5.6-sol | 输入 ¥1.3 / 输出 ¥7.5 / 缓存 ¥0.1 / 写入 ¥1.6 | 0% | — | — | — |
| 「企业-不降智」OpenAI | gpt-5.6-sol | 输入 ¥2.1 / 输出 ¥12.6 / 缓存 ¥0.2 / 写入 ¥2.6 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 「Plus」OpenAI | gpt-5.6-terra | 输入 ¥0.3 / 输出 ¥1.9 / 缓存 ¥0 / 写入 ¥0.4 | 0% | — | — | — |
| 「Pro」OpenAI | gpt-5.6-terra | 输入 ¥0.5 / 输出 ¥3 / 缓存 ¥0 / 写入 ¥0.6 | 0% | — | — | — |
| 「企业-不降智」OpenAI | gpt-5.6-terra | 输入 ¥0.8 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥1.1 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 「Plus」OpenAI | gpt-5.5 | 输入 ¥0.8 / 输出 ¥4.8 / 缓存 ¥0.1 / 写入 ¥0 | 0% | — | — | — |
| 「Pro」OpenAI | gpt-5.5 | 输入 ¥1.3 / 输出 ¥7.5 / 缓存 ¥0.1 / 写入 ¥0 | 0% | — | — | — |
| 「企业-不降智」OpenAI | gpt-5.5 | 输入 ¥2.1 / 输出 ¥12.6 / 缓存 ¥0.2 / 写入 ¥0 | 0% | — | — | — |
5.0 / 5 from 1 approved reviews
gpt首字延迟很低，tps很高，用起来很舒心，值得推荐
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.