Fable 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 |
|---|---|---|---|---|---|---|
| Claude-Max | claude-fable-5 | 输入 ¥12.5 / 输出 ¥62.5 / 缓存 ¥1.25 / 写入 ¥25 | 0% | — | — | — |
Site descriptions, notices, and reviews are shown in the language in which they were submitted.
Keda8AI 是一家可靠高效的 API 中转服务商,提供 Claude Code、Codex、DeepSeek、Grok 等多种服务的中转。 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. 推特 @Keda8_ai 运营qq 14545
Price listing
Fable 5
1 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
2 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Terra
1 public records are listed; open the full page to review details as needed.
Price listing
GPT Image 2
3 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.
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 |
|---|---|---|---|---|---|---|
| Claude-Max | claude-fable-5 | 输入 ¥12.5 / 输出 ¥62.5 / 缓存 ¥1.25 / 写入 ¥25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Kiro-Lite | claude-opus-4-8 | 输入 ¥0.85 / 输出 ¥4.25 / 缓存 ¥0.085 / 写入 ¥1.7 | 0% | — | — | — |
| Claude-Max | claude-opus-4-8 | 输入 ¥6.25 / 输出 ¥31.25 / 缓存 ¥0.625 / 写入 ¥12.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Kiro-Lite | claude-opus-4-7 | 输入 ¥0.85 / 输出 ¥4.25 / 缓存 ¥0.085 / 写入 ¥1.7 | 0% | — | — | — |
| Claude-Max | claude-opus-4-7 | 输入 ¥6.25 / 输出 ¥31.25 / 缓存 ¥0.625 / 写入 ¥12.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Kiro-Lite | claude-sonnet-5 | 输入 ¥0.34 / 输出 ¥1.7 / 缓存 ¥0.034 / 写入 ¥0.68 | 0% | — | — | — |
| Claude-Max | claude-sonnet-5 | 输入 ¥2.5 / 输出 ¥12.5 / 缓存 ¥0.25 / 写入 ¥5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ChatGPT-Pro+ | gpt-5.6-sol | 输入 ¥1.2 / 输出 ¥6 / 缓存 ¥0.12 / 写入 ¥1.5 | 0% | — | — | — |
| ChatGPT-ProMax | gpt-5.6-sol | 输入 ¥2 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥2.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ChatGPT-ProMax | gpt-5.6-terra | 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥1.25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ChatGPT-Image | gpt-image-2 | ¥0.65 / 次 | - | — | — | — |
| ChatGPT-ProMax | gpt-image-2 | ¥0.65 / 次 | - | — | — | — |
| Keda-Pro | gpt-image-2 | ¥0.65 / 次 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Kiro-Lite | claude-opus-4-6 | 输入 ¥0.85 / 输出 ¥4.25 / 缓存 ¥0.085 / 写入 ¥1.7 | 0% | — | — | — |
| Claude-Max | claude-opus-4-6 | 输入 ¥6.25 / 输出 ¥31.25 / 缓存 ¥0.625 / 写入 ¥12.5 | 0% | — | — | — |
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.