H Hvoy AI
Back to gateway directory
Site domain
api.tianshu.surf
Established
2026-11-14
Covered models
Fable 5 / Opus 4.8 / Opus 4.7 / Sonnet 5 / GPT 5.6 Sol / GPT 5.6 Terra / Opus 4.6
Public records
64 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

本站提供gpt,claude,国产模型 API中转服务,只做优质,主打稳定不降智、低倍率、售后有保障。兼顾模型质量与调用稳定性,让日常使用、编程开发和应用接入更省心;低倍率计费,让使用成本更实惠;提供售后支持,从接入配置到使用过程中的问题,客服会协助处理。用得起、用得稳,遇到问题找得到人。

Model coverage summary

Price listing

Fable 5

2 public records are listed; open the full page to review details as needed.

Price listing

Opus 4.8

3 public records are listed; open the full page to review details as needed.

Price listing

Opus 4.7

3 public records are listed; open the full page to review details as needed.

Price listing

Sonnet 5

3 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

Opus 4.6

3 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.

Fable 5

2 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 ¥60 / 输出 ¥60 / 缓存 ¥0 / 写入 ¥0 0% — — —
CCMAX原生0注入 claude-fable-5 输入 ¥67.5 / 输出 ¥67.5 / 缓存 ¥0 / 写入 ¥0 0% — — —

Opus 4.8

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Kiro claude-opus-4-8 输入 ¥0.55 / 输出 ¥2.75 / 缓存 ¥0.055 / 写入 ¥0.6875 0% — — —
CCMAX claude-opus-4-8 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 0% — — —
CCMAX原生0注入 claude-opus-4-8 输入 ¥4.5 / 输出 ¥22.5 / 缓存 ¥0.45 / 写入 ¥5.63 0% — — —

Opus 4.7

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Kiro claude-opus-4-7 输入 ¥0.55 / 输出 ¥2.75 / 缓存 ¥0.055 / 写入 ¥0.6875 0% — — —
CCMAX claude-opus-4-7 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 0% — — —
CCMAX原生0注入 claude-opus-4-7 输入 ¥4.5 / 输出 ¥22.5 / 缓存 ¥0.45 / 写入 ¥5.63 0% — — —

Sonnet 5

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Kiro claude-sonnet-5 输入 ¥8.25 / 输出 ¥8.25 / 缓存 ¥0 / 写入 ¥0 0% — — —
CCMAX claude-sonnet-5 输入 ¥60 / 输出 ¥60 / 缓存 ¥0 / 写入 ¥0 0% — — —
CCMAX原生0注入 claude-sonnet-5 输入 ¥67.5 / 输出 ¥67.5 / 缓存 ¥0 / 写入 ¥0 0% — — —

GPT 5.6 Sol

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
gpt不降智特惠 gpt-5.6-sol 输入 ¥0.225 / 输出 ¥1.35 / 缓存 ¥0 / 写入 ¥0.2813 -10% — — —
gpt-plus gpt-5.6-sol 输入 ¥0.4 / 输出 ¥2.4 / 缓存 ¥0 / 写入 ¥0.5 0% — — —
gpt-pro gpt-5.6-sol 输入 ¥0.55 / 输出 ¥3.3 / 缓存 ¥0 / 写入 ¥0.6875 0% — — —

GPT 5.6 Terra

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
gpt-plus gpt-5.6-terra 输入 ¥0.2 / 输出 ¥1.2 / 缓存 ¥0 / 写入 ¥0.25 0% — — —
gpt-pro gpt-5.6-terra 输入 ¥0.275 / 输出 ¥1.65 / 缓存 ¥0 / 写入 ¥0.3438 0% — — —
gpt-pro企业 gpt-5.6-terra 输入 ¥0.375 / 输出 ¥2.25 / 缓存 ¥0 / 写入 ¥0.4688 0% — — —

Opus 4.6

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
Kiro claude-opus-4-6 输入 ¥0.55 / 输出 ¥2.75 / 缓存 ¥0.055 / 写入 ¥0.6875 0% — — —
CCMAX claude-opus-4-6 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 0% — — —
CCMAX原生0注入 claude-opus-4-6 输入 ¥4.5 / 输出 ¥22.5 / 缓存 ¥0.45 / 写入 ¥5.63 0% — — —

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.