H Hvoy AI
Back to gateway directory
Site domain
modelsell.com
Established
2025-07-01
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 / GPT Image 2 / Opus 4.6
Public records
171 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

企业级Models 统一 API 网关,统一接入 OpenAI、Claude、Gemini、DeepSeek 和私有渠道,并提供共享密钥、计费、故障路由与实时请求可见性。 折扣最低 0.5 折

Model coverage summary

Price listing

Fable 5

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

Price listing

Opus 4.8

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

Price listing

Opus 4.7

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

Price listing

Sonnet 5

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

Price listing

GPT 5.6 Sol

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

Price listing

GPT 5.6 Terra

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

Price listing

GPT 5.5

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

Price listing

GLM 5.2

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

Price listing

GPT Image 2

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

Price listing

Opus 4.6

9 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
Claude kiro claude-fable-5 输入 ¥6.8 / 输出 ¥34 / 缓存 ¥0.68 / 写入 ¥13.6 -2.9%
CCMax claude-fable-5 输入 ¥20.4 / 输出 ¥102 / 缓存 ¥2.04 / 写入 ¥40.8 -2.9%
AmazonBedrock claude-fable-5 输入 ¥40.8 / 输出 ¥204 / 缓存 ¥4.08 / 写入 ¥81.6 -42%

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 kiro claude-opus-4-8 输入 ¥3.4 / 输出 ¥17 / 缓存 ¥0.34 / 写入 ¥6.8 -2.9%
CCMax claude-opus-4-8 输入 ¥10.2 / 输出 ¥51 / 缓存 ¥1.02 / 写入 ¥20.4 -2.9%
AmazonBedrock claude-opus-4-8 输入 ¥20.4 / 输出 ¥102 / 缓存 ¥2.04 / 写入 ¥40.8 -42%

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 kiro claude-opus-4-7 输入 ¥3.4 / 输出 ¥17 / 缓存 ¥0.34 / 写入 ¥6.8 -2.9%
CCMax claude-opus-4-7 输入 ¥10.2 / 输出 ¥51 / 缓存 ¥1.02 / 写入 ¥20.4 -2.9%
AmazonBedrock claude-opus-4-7 输入 ¥20.4 / 输出 ¥102 / 缓存 ¥2.04 / 写入 ¥40.8 -42%

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 kiro claude-sonnet-5 输入 ¥1.36 / 输出 ¥6.8 / 缓存 ¥0.136 / 写入 ¥2.72 -2.9%
CCMax claude-sonnet-5 输入 ¥4.08 / 输出 ¥20.4 / 缓存 ¥0.408 / 写入 ¥8.16 -2.9%
AmazonBedrock claude-sonnet-5 输入 ¥8.16 / 输出 ¥40.8 / 缓存 ¥0.816 / 写入 ¥16.32 -42%

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特价 gpt-5.6-sol 输入 ¥3.4 / 输出 ¥20.4 / 缓存 ¥0.34 / 写入 ¥4.25 -2.9%
Azure gpt-5.6-sol 输入 ¥20.4 / 输出 ¥122.4 / 缓存 ¥2.04 / 写入 ¥25.5 -42%
GPT官+AZ 混合 gpt-5.6-sol 输入 ¥20.4 / 输出 ¥122.4 / 缓存 ¥2.04 / 写入 ¥25.5 -2.9%

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特价 gpt-5.6-terra 输入 ¥1.36 / 输出 ¥8.16 / 缓存 ¥0.136 / 写入 ¥1.7 -2.9%
Azure gpt-5.6-terra 输入 ¥8.16 / 输出 ¥48.96 / 缓存 ¥0.816 / 写入 ¥10.2 -42%
GPT官+AZ 混合 gpt-5.6-terra 输入 ¥8.16 / 输出 ¥48.96 / 缓存 ¥0.816 / 写入 ¥10.2 -2.9%

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
GPT特价 gpt-5.5 输入 ¥3.4 / 输出 ¥20.4 / 缓存 ¥0.34 / 写入 ¥0 -2.9%
Azure gpt-5.5 输入 ¥20.4 / 输出 ¥122.4 / 缓存 ¥2.04 / 写入 ¥0 -42%
GPT官+AZ 混合 gpt-5.5 输入 ¥20.4 / 输出 ¥122.4 / 缓存 ¥2.04 / 写入 ¥0 -2.9%

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
火山引擎特价 glm-5.2 输入 ¥4.28 / 输出 ¥13.46 / 缓存 ¥0.7956 / 写入 ¥0 0%
Volcengine glm-5.2 输入 ¥8.76 / 输出 ¥27.53 / 缓存 ¥1.63 / 写入 ¥0 -2.9%
Alibaba glm-5.2 输入 ¥9.52 / 输出 ¥29.92 / 缓存 ¥1.77 / 写入 ¥0 -2.9%

GPT Image 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
GPT官+AZ 混合 gpt-image-2 输入 ¥32.64 / 输出 ¥122.4 / 缓存 ¥0 / 写入 ¥0 -2.9%
OpenAI gpt-image-2 输入 ¥32.64 / 输出 ¥122.4 / 缓存 ¥0 / 写入 ¥0 -42%
标准按次 gpt-image-2 输入 ¥54.4 / 输出 ¥204 / 缓存 ¥0 / 写入 ¥0 -2.9%

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
Claude kiro claude-opus-4-6 输入 ¥3.4 / 输出 ¥17 / 缓存 ¥0.34 / 写入 ¥6.8 -2.9%
CCMax claude-opus-4-6 输入 ¥10.2 / 输出 ¥51 / 缓存 ¥1.02 / 写入 ¥20.4 -2.9%
AmazonBedrock claude-opus-4-6 输入 ¥20.4 / 输出 ¥102 / 缓存 ¥2.04 / 写入 ¥40.8 -42%

Site notices

支持最新的claude-opus-5,性能接近 fable5,但是价值只有一半。

支持最新的claude-opus-5,性能接近 fable5,但是价值只有一半。 claude-sonnet-5和claude-fable-5 此前已支持,目前已经全面支持 claude 5 全家桶

gpt-5.6-luna、gpt-5.6-terra和gpt-5.6-sol现已上线

gpt-5.6-luna、gpt-5.6-terra和gpt-5.6-sol现已上线

海外版Seedacne2.0普通版本:

海外版Seedacne2.0普通版本: dreamina-seedance-2-0-260128 dreamina-seedance-2-0-fast-260128 海外版Seedacne2.0解锁成人,支持 NSFW版本: dreamina-seedance-2-0-fast-ep dreamina-seedance-2-0-ep 国内版Seedacne2.0,新增 mini版本 doubao-seedance-2-0-260128 doubao-seedance-2-0-fast-260128 doubao-seedance-2-0-mini-260615 支持真人素材,查看接口文档 查看更多模型价格 以上所有模型 92 折供应 ,即将发布支持 Seedance2.5 版本,敬请期待

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.