H Hvoy AI
Back to gateway directory
Site domain
fishxcode.com
Established
2026-01-01
Covered models
Fable 5 / Opus 4.8 / Opus 4.7 / Sonnet 5 / GPT 5.6 Sol / GPT 5.6 Terra / GPT 5.5 / GLM 5.2 / Opus 4.6
Public records
369 public records
User feedback
35 up / 3 down

Site descriptions, notices, and reviews are shown in the language in which they were submitted.

Site introduction

企业级 Claude API 官方通道中转 仅接 Anthropic 官方通道,不走逆向。智能缓存命中超 90%,比直连官方节省 60%+ Token 成本,兼容官方 API 接入方式,并支持企业开具正规增值税发票。

Model coverage summary

Price listing

Fable 5

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

Price listing

Opus 4.8

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

Price listing

Opus 4.7

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

Price listing

Sonnet 5

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

Price listing

GPT 5.6 Sol

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

Price listing

GPT 5.6 Terra

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

Price listing

GPT 5.5

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

Price listing

GLM 5.2

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

Price listing

Opus 4.6

25 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

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
claudemax20 claude-fable-5 输入 ¥141 / 输出 ¥141 / 缓存 ¥0 / 写入 ¥0 +650% — — —
CCMax 0注入 限CC claude-fable-5 输入 ¥180 / 输出 ¥180 / 缓存 ¥0 / 写入 ¥0 0% — — —
claudemax2 claude-fable-5 输入 ¥180 / 输出 ¥180 / 缓存 ¥0 / 写入 ¥0 +650% — — —

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
claude-awsq claude-opus-4-8 输入 ¥52.5 / 输出 ¥262.5 / 缓存 ¥0 / 写入 ¥0 +1400% — — —
vertex-claude claude-opus-4-8 输入 ¥105 / 输出 ¥525 / 缓存 ¥0 / 写入 ¥0 +1400% — — —
claude_supplier claude-opus-4-8 输入 ¥120 / 输出 ¥600 / 缓存 ¥0 / 写入 ¥0 +1400% — — —

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
claude_supplier claude-opus-4-7-thinking 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥16 0% — — —
claude_venlacy claude-opus-4-7-thinking 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥16 0% — — —
enterprise-claude claude-opus-4-7 输入 ¥9 / 输出 ¥1125 / 缓存 ¥0 / 写入 ¥0 -40% — — —

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
claude-awsq claude-sonnet-5 输入 ¥52.5 / 输出 ¥52.5 / 缓存 ¥0 / 写入 ¥0 +3650% — — —
vertex-claude claude-sonnet-5 输入 ¥105 / 输出 ¥105 / 缓存 ¥0 / 写入 ¥0 +3650% — — —
claude_supplier claude-sonnet-5 输入 ¥120 / 输出 ¥120 / 缓存 ¥0 / 写入 ¥0 +3650% — — —

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
codex_plus gpt-5.6-sol 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 0% — — —
codex_supplier gpt-5.6-sol 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 0% — — —
codex_team gpt-5.6-sol 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 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
codex_plus gpt-5.6-terra 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 0% — — —
codex_supplier gpt-5.6-terra 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 0% — — —
codex_team gpt-5.6-terra 输入 ¥18.75 / 输出 ¥150 / 缓存 ¥0 / 写入 ¥0 0% — — —

GPT 5.5

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
codex_plus gpt-5.5 输入 ¥18.75 / 输出 ¥112.5 / 缓存 ¥0 / 写入 ¥0 +1400% — — —
codex_supplier gpt-5.5 输入 ¥18.75 / 输出 ¥112.5 / 缓存 ¥0 / 写入 ¥0 +1400% — — —
codex_team gpt-5.5 输入 ¥18.75 / 输出 ¥112.5 / 缓存 ¥0 / 写入 ¥0 +1400% — — —

GLM 5.2

3 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
deepseek glm-5.2 输入 ¥4 / 输出 ¥14 / 缓存 ¥1 / 写入 ¥14 0% — — —
china glm-5.2 输入 ¥0 / 输出 ¥22.4 / 缓存 ¥1.6 / 写入 ¥22.4 - — — —
default glm-5.2 输入 ¥0 / 输出 ¥84 / 缓存 ¥6 / 写入 ¥84 - — — —

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_svip claude-opus-4-6 输入 ¥0 / 输出 ¥67.5 / 缓存 ¥0 / 写入 ¥0 - — — —
vertex-claude claude-opus-4-6 输入 ¥105 / 输出 ¥525 / 缓存 ¥0 / 写入 ¥0 +1400% — — —
claude_supplier claude-opus-4-6 输入 ¥120 / 输出 ¥600 / 缓存 ¥0 / 写入 ¥0 +1400% — — —

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.