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 |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-fable-5 | 输入 ¥10 / 输出 ¥50 / 缓存 ¥1 / 写入 ¥20 | +25% | — | — | — |
Site descriptions, notices, and reviews are shown in the language in which they were submitted.
橙子中转站提供 OpenAI 与 Claude 系列模型的 API 中转服务,适用于编程开发、AI 工具接入、日常办公和内容创作。主推 0.4 倍率的「企业级稳定」GPT 官方 Key 分组(永不降智),以及 0.8 倍率的「企业级稳定」CCMax 分组。两大分组近期缓存读取占比均超过 99%,首字响应 P50 分别约为 3.9 秒和 2.3 秒,为重视响应速度和调用成本的用户提供选择。站内提供余额管理、使用记录、费用明细及渠道状态查询,方便随时了解调用情况与使用成本。CCMax 分组目前仅支持 Claude Code CLI 或 Desktop 客户端及vsc插件等,后续会逐步开放。
Price listing
Fable 5
1 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.8
1 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.7
1 public records are listed; open the full page to review details as needed.
Price listing
Sonnet 5
1 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
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 4.6
1 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 |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-fable-5 | 输入 ¥10 / 输出 ¥50 / 缓存 ¥1 / 写入 ¥20 | +25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-opus-4-8 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥10 | +25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-opus-4-7 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥10 | +25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-sonnet-5 | 输入 ¥2 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥4 | +25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【掺水全退】gpt稳定不降智(tps高,纯pro号池) | gpt-5.6-sol | 输入 ¥0.5 / 输出 ¥3 / 缓存 ¥0.05 / 写入 ¥0.625 | 0% | — | — | — |
| 【特惠】低价gpt官key分组 | gpt-5.6-sol | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥1.88 | 0% | — | — | — |
| 【企业级稳定】gpt官方key(全天在线,不降智,缓存99) | gpt-5.6-sol | 输入 ¥2 / 输出 ¥12 / 缓存 ¥0.2 / 写入 ¥2.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【特惠】低价gpt官key分组 | gpt-5.6-terra | 输入 ¥0.6 / 输出 ¥3.6 / 缓存 ¥0.06 / 写入 ¥0.75 | 0% | — | — | — |
| 【企业级稳定】gpt官方key(全天在线,不降智,缓存99) | gpt-5.6-terra | 输入 ¥0.8 / 输出 ¥4.8 / 缓存 ¥0.08 / 写入 ¥1 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【特惠】低价gpt官key分组 | gpt-5.5 | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥0 | 0% | — | — | — |
| 【企业级稳定】gpt官方key(全天在线,不降智,缓存99) | gpt-5.5 | 输入 ¥2 / 输出 ¥12 / 缓存 ¥0.2 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【企业级稳定】正价ccmax | claude-opus-4-6 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥10 | +25% | — | — | — |
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.