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 |
|---|---|---|---|---|---|---|
| ccmax | claude-fable-5 | 输入 ¥52.94 / 输出 ¥264.71 / 缓存 ¥5.29 / 写入 ¥66.18 | +1900% | — | — | — |
- Site domain
- kezhanai.com
- Established
- 2026-08-01
- Covered models
- Fable 5 / Opus 4.8 / Opus 4.7 / Sonnet 5 / GPT 5.6 Sol / GPT 5.6 Terra / GPT 5.5 / GPT Image 2 / Opus 4.6
- Public records
- 17 public records
- User feedback
- 0 up / 0 down
Site descriptions, notices, and reviews are shown in the language in which they were submitted.
Site introduction
客栈 AI（kezhanai） 是一个集多模型调用、在线对话与 API 接入于一体的 AI 服务平台，面向开发者、内容创作者，以及希望将 AI 接入日常工作和业务应用的个人与团队。站点以武侠客栈为特色，将模型选择、密钥管理、账户充值、用量查询和售后支持集中在一处，让用户更方便地开始使用 AI，也更清楚地掌握使用成本。 - 多模型集中管理，接入更方便。 在“藏经阁”查看模型、接口类型与价格，按需求选择适合的能力；既可以在“问剑台”进行在线对话，也可以创建 API Key，将模型接入自己的应用和工作流。平台提供接入手册及代码示例，减少从选模型到完成首次调用的操作成本。 - 按需充值、按使用计费，账目清楚。 不同模型根据 Token 用量、调用次数或对应计价规则结算，模型目录展示所选分组的价格，调用记录可核对模型、用量与费用。用户可以结合预算选择模型，并为不同应用设置独立令牌额度。具体单价、缓存及附加费用，以站内价格说明和最终账单为准。 - 重视服务稳定性，也提供问题排查入口。 项目通过渠道管理、实际调用验证、部署健康检查和备份恢复机制维护服务，并提供“驿路状态”、服务公告与调用日志，帮助用户检查连接、了解服务调整和定位异常。具体模型的可用性与响应速度仍受上游服务、网络及并发情况影响。 - 售后有入口，处理过程可追踪。 遇到账户登录、充值账务或模型接入问题，可以通过“飞鸽传书”提交工单、补充说明、查看处理状态与回复，历史沟通集中保存。平台还提供个人及企业发票申请入口，支持审核进度查询和审核完成后的发票 PDF 下载。 - 兼顾使用管理与长期体验。 支持按应用创建独立 API Key，配置额度、有效期、模型权限及 IP 限制；同时设有签到、邀请和成长权益功能，用户可在站内查看当前开放的活动及适用规则。武侠客栈风格贯穿整个使用过程，让工具平台多一份辨识度与亲切感。
Model coverage summary
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
1 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 5.5
1 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
1 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.
Opus 4.8
1 public records are listed; open the full page to review details as needed.| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ccmax | claude-opus-4-8 | 输入 ¥26.47 / 输出 ¥132.35 / 缓存 ¥2.65 / 写入 ¥33.09 | +1900% | — | — | — |
Opus 4.7
1 public records are listed; open the full page to review details as needed.| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ccmax | claude-opus-4-7 | 输入 ¥26.47 / 输出 ¥132.35 / 缓存 ¥2.65 / 写入 ¥33.09 | +1900% | — | — | — |
Sonnet 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 |
|---|---|---|---|---|---|---|
| ccmax | claude-sonnet-5 | 输入 ¥10.59 / 输出 ¥52.94 / 缓存 ¥1.06 / 写入 ¥13.24 | +1900% | — | — | — |
GPT 5.6 Sol
1 public records are listed; open the full page to review details as needed.| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gpt-pro | gpt-5.6-sol | 输入 ¥2.59 / 输出 ¥12.94 / 缓存 ¥0.2588 / 写入 ¥3.24 | +1900% | — | — | — |
GPT 5.6 Terra
1 public records are listed; open the full page to review details as needed.| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gpt-pro | gpt-5.6-terra | 输入 ¥1.29 / 输出 ¥7.76 / 缓存 ¥0.1294 / 写入 ¥1.62 | +1900% | — | — | — |
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 |
|---|---|---|---|---|---|---|
| gpt-pro | gpt-5.5 | 输入 ¥3.24 / 输出 ¥19.41 / 缓存 ¥0.3235 / 写入 ¥3.24 | +1900% | — | — | — |
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 |
|---|---|---|---|---|---|---|
| gpt-pro | gpt-image-2 | 输入 ¥3.24 / 输出 ¥19.41 / 缓存 ¥0.8088 / 写入 ¥3.24 | +1900% | — | — | — |
Opus 4.6
1 public records are listed; open the full page to review details as needed.| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| ccmax | claude-opus-4-6 | 输入 ¥26.47 / 输出 ¥132.35 / 缓存 ¥2.65 / 写入 ¥33.09 | +1900% | — | — | — |
Site notices
有问题请提交工单。
有问题请提交工单。
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.