Site descriptions, notices, and reviews are shown in the language in which they were submitted.
该站点主要服务于中转站，需要稳定低价上游的站长 gpt 池倍率最低0.01 claude 池最低0.08倍率 不限并发数，rpm容量为100000+，7天稳定性达到100% 支持发票，支持退款
Price listing
Fable 5
4 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.8
5 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.7
5 public records are listed; open the full page to review details as needed.
Price listing
Sonnet 5
4 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Sol
4 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
GLM 5.2
1 public records are listed; open the full page to review details as needed.
Price listing
GPT Image 2
6 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.6
5 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-kiro | claude-fable-5 | 输入 ¥2 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥4 | 0% | — | — | — |
| claude-awsq | claude-fable-5 | 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥8 | 0% | — | — | — |
| claude 满血 | claude-fable-5 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥10 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4-8 | 输入 ¥0 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥2 | - | — | — | — |
| 企业claude分组 | claude-opus-4-8 | 输入 ¥6.5 / 输出 ¥32.5 / 缓存 ¥0.65 / 写入 ¥13 | 0% | — | — | — |
| claude-awsq | claude-opus-4-8 | 输入 ¥0 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥4 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4-7 | 输入 ¥0 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥2 | - | — | — | — |
| 企业claude分组 | claude-opus-4-7 | 输入 ¥6.5 / 输出 ¥32.5 / 缓存 ¥0.65 / 写入 ¥13 | 0% | — | — | — |
| claude-awsq | claude-opus-4-7 | 输入 ¥0 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥4 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-sonnet-5 | 输入 ¥0.6 / 输出 ¥3 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| claude-awsq | claude-sonnet-5 | 输入 ¥1.2 / 输出 ¥6 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| claude 满血 | claude-sonnet-5 | 输入 ¥1.5 / 输出 ¥7.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 福利gpt | gpt-5.6-sol | 输入 ¥0.5 / 输出 ¥3 / 缓存 ¥0.05 / 写入 ¥0 | -50% | — | — | — |
| 专用gpt | gpt-5.6-sol | 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥0 | 0% | — | — | — |
| gpt pro | gpt-5.6-sol | 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 福利gpt | gpt-5.6-terra | 输入 ¥0.2 / 输出 ¥1.2 / 缓存 ¥0.02 / 写入 ¥0 | -50% | — | — | — |
| 专用gpt | gpt-5.6-terra | 输入 ¥0.4 / 输出 ¥2.4 / 缓存 ¥0.04 / 写入 ¥0 | 0% | — | — | — |
| 企业gpt（不降智） | gpt-5.6-terra | 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 国产模型 | glm-5.2 | 输入 ¥5 / 输出 ¥15 / 缓存 ¥1 / 写入 ¥5 | +11% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 生图 | gpt-image-2 | ¥0.06 / 次 | - | — | — | — |
| image-4k | gpt-image-2 | ¥0.06 / 次 | - | — | — | — |
| 福利gpt | gpt-image-2 | ¥0.1 / 次 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4-6 | 输入 ¥0 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥2 | - | — | — | — |
| 企业claude分组 | claude-opus-4-6 | 输入 ¥6.5 / 输出 ¥32.5 / 缓存 ¥0.65 / 写入 ¥13 | 0% | — | — | — |
| claude-awsq | claude-opus-4-6 | 输入 ¥0 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥4 | - | — | — | — |
gpt-6.1-terra已上全部gpt分组
金贝贝更新公告： grok分组技术已突破，满智力，首token稳定2s内 claude-sonnet-5-5已上全部claude分组 技术突破，Gpt全分组不降智 deepseek最新模型已上国产模型分组
gemini-4-argon已上线
@全体成员 gpt新模型和grok新模型已上 claude新模型已上
模型更新公告 qwen3.8-max（国产模型分组） minimax-m3（国产模型分组） glm-5.3-flash（国产模型分组） claude-fable-5-1（cc max分组） 已上线 @全体成员
3.0 / 5 from 2 approved reviews
两个网址都进不去。已经接近一个月了，是跑路了，还是发生其他什么事情了？
Site reply
美国全局魔法 https://downstream.jbbtoken.cn/
我主要拿金贝贝接 Codex 使用，整体体验不错。配置文档写得比较细，Base URL、API Key、模型分组这些都有说明，照着教程操作基本就能跑起来，不需要到处找配置方法。模型选择也比较丰富，OpenAI、Claude、Gemini、Grok 等都能在一个平台管理，模型价格和分组倍率可以直接查看。使用过程中偶尔遇到报错，文档里的排查说明也比较实用。目前用下来整体比较省心。
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.