H Hvoy AI
Back to gateway directory
Site domain
yomiapi.com
Established
2026-07-25
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
58 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

Yomi API 是 AI 大模型 API 聚合平台。传统中转站只解决"连得上",Yomi 更进一步——专注解决"用得高效":把多模型选型、比价、性能监控、统一计费整合进一套系统。 QQ群不定期发放大额福利:1078436366 稳定接入 GPT、Claude、Gemini、DeepSeek 等 40+ 模型,全系 OpenAI 兼容、零改造接入;模型广场实时比价 + 24h 性能快照,让"哪个最划算/最快/最稳"变成可量化决策。按 token 透明计费、无隐藏扣量,一张账单统管全模型消耗,最低可至官方价一折,即充即用、无月费无最低消费。 东京高防节点 + Cloudflare 加速,SLA 保障,控制台实时公开延迟/TPS/成功率;提供全天售后,不满意随时可退款,尤其适配企业级用户规模化调用。

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

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

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

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
Claude-MAX(cc专用,仅接cli) claude-fable-5 输入 ¥20.9 / 输出 ¥104.5 / 缓存 ¥2.09 / 写入 ¥26.13 -3%
Claude官方Max线路 claude-fable-5 输入 ¥23.6 / 输出 ¥117.99 / 缓存 ¥2.36 / 写入 ¥29.5 -3%

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
ClaudePlus线路(不支持fable) claude-opus-4-8 输入 ¥4.05 / 输出 ¥20.23 / 缓存 ¥0.4045 / 写入 ¥5.06 -3%
Claude-MAX(cc专用,仅接cli) claude-opus-4-8 输入 ¥10.45 / 输出 ¥52.25 / 缓存 ¥1.05 / 写入 ¥13.06 -3%
Claude官方Max线路 claude-opus-4-8 输入 ¥11.8 / 输出 ¥58.99 / 缓存 ¥1.18 / 写入 ¥14.75 -3%

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
ClaudePlus线路(不支持fable) claude-opus-4-7 输入 ¥4.05 / 输出 ¥20.23 / 缓存 ¥0.4045 / 写入 ¥5.06 -3%
Claude-MAX(cc专用,仅接cli) claude-opus-4-7 输入 ¥10.45 / 输出 ¥52.25 / 缓存 ¥1.05 / 写入 ¥13.06 -3%
Claude官方Max线路 claude-opus-4-7 输入 ¥11.8 / 输出 ¥58.99 / 缓存 ¥1.18 / 写入 ¥14.75 -3%

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
ClaudePlus线路(不支持fable) claude-sonnet-5 输入 ¥1.62 / 输出 ¥8.09 / 缓存 ¥0.1618 / 写入 ¥2.02 -3%
Claude-MAX(cc专用,仅接cli) claude-sonnet-5 输入 ¥4.18 / 输出 ¥20.9 / 缓存 ¥0.418 / 写入 ¥5.23 -3%
Claude官方Max线路 claude-sonnet-5 输入 ¥4.72 / 输出 ¥23.6 / 缓存 ¥0.4719 / 写入 ¥5.9 -3%

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 特惠线路2 gpt-5.6-sol 输入 ¥3.03 / 输出 ¥18.2 / 缓存 ¥0.3034 / 写入 ¥3.79 -3%
GPT 特惠线路优化 gpt-5.6-sol 输入 ¥3.03 / 输出 ¥18.2 / 缓存 ¥0.3034 / 写入 ¥3.79 -3%
GPT-PRO专线 gpt-5.6-sol 输入 ¥4.05 / 输出 ¥24.27 / 缓存 ¥0.4045 / 写入 ¥5.06 +0.1%

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 特惠线路2 gpt-5.6-terra 输入 ¥1.21 / 输出 ¥7.28 / 缓存 ¥0.1214 / 写入 ¥1.52 -3%
GPT 特惠线路优化 gpt-5.6-terra 输入 ¥1.21 / 输出 ¥7.28 / 缓存 ¥0.1214 / 写入 ¥1.52 -3%
GPT-PRO专线 gpt-5.6-terra 输入 ¥1.62 / 输出 ¥9.71 / 缓存 ¥0.1618 / 写入 ¥2.02 +0.1%

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 特惠线路2 gpt-5.5 输入 ¥3.03 / 输出 ¥18.2 / 缓存 ¥0.3034 / 写入 ¥0 -3%
GPT 特惠线路优化 gpt-5.5 输入 ¥3.03 / 输出 ¥18.2 / 缓存 ¥0.3034 / 写入 ¥0 -3%
GPT-PRO专线 gpt-5.5 输入 ¥4.05 / 输出 ¥24.27 / 缓存 ¥0.4045 / 写入 ¥0 +0.1%

GLM 5.2

1 public records are listed; open the full page to review details as needed.
Channel Provider model Current price Price trend Uptime Fake % Latency
智谱 满血API折扣 glm-5.2 输入 ¥3.88 / 输出 ¥13.55 / 缓存 ¥0.9698 / 写入 ¥0 -34%

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
image2专用(仅生图) gpt-image-2 输入 ¥505.66 / 输出 ¥1011.31 / 缓存 ¥0 / 写入 ¥0 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
ClaudePlus线路(不支持fable) claude-opus-4-6 输入 ¥4.05 / 输出 ¥20.23 / 缓存 ¥0.4045 / 写入 ¥5.06 -3%
Claude-MAX(cc专用,仅接cli) claude-opus-4-6 输入 ¥10.45 / 输出 ¥52.25 / 缓存 ¥1.05 / 写入 ¥13.06 -3%
Claude官方Max线路 claude-opus-4-6 输入 ¥11.8 / 输出 ¥58.99 / 缓存 ¥1.18 / 写入 ¥14.75 -3%

Site notices

DeepSeek 官方近期调整了 API 模型的定价及计费规则,并推出峰时 / 闲时计费机制。

DeepSeek 官方近期调整了 API 模型的定价及计费规则,并推出峰时 / 闲时计费机制。 为与上游官方价格保持一致,Yomi API 将于 2026 年 8 月 17 日起同步调整 DeepSeek 相关模型价格,涉及 DeepSeek V4 系列模型的输入、缓存命中及输出 Token 计费。 本次调整仅为同步上游官方价格,不涉及其他模型及服务。具体价格请以 Yomi API 模型广场及价格页面显示为准。 感谢您的理解与支持。

智谱国产模型折扣倍率由 0.6 下调至 0.35,调整即刻生效。

智谱国产模型折扣倍率由 0.6 下调至 0.35,调整即刻生效。存量密钥与调用方式无需任何变更,感谢您的支持。

如调用时出现 model not found、no available channel for model 、模型不存在等错误,请首先检查模型名称是否填写正确。

如调用时出现 model not found、no available channel for model 、模型不存在等错误,请首先检查模型名称是否填写正确。 以 GPT-5.6-sol 为例,正确的模型名称为: gpt-5.6-sol 错误示例: gpt5.6、gpt5.6sol、在模型名称栏填写 API Key(密钥)等。 请注意,模型名称必须严格按照平台提供的 Model ID 填写,不要自行简写、修改或猜测。 Yomi 的「模型服务」页面已提供对应模型的准确模型名称,调用前请以页面显示的名称为准,直接复制使用即可。 模型名称 ≠ API Key(密钥),两者属于完全不同的参数,请勿混淆。

以 GPT-5.6-sol 为例,正确的模型名称为:\ngpt-5.6-sol\n错误示例:gpt5.6、gpt5.6sol、在模型名称栏填写 API Key(

以 GPT-5.6-sol 为例,正确的模型名称为:\ngpt-5.6-sol\n错误示例:gpt5.6、gpt5.6sol、在模型名称栏填写 API Key(密钥)等。\n模型名称必须严格按照平台提供的 Model ID 填写,请勿自行简写、修改或猜测。\nYomi「模型服务」页面已提供准确的模型名称,请以页面显示的名称为准,直接复制使用。\n模型名称 ≠ API Key,请勿混淆。

DeepSeek Harness(dsh)已更新至0.1.0-rc.6\n升级方式:npm install -g @deepseek-ai/dsh\n升级后重启

DeepSeek Harness(dsh)已更新至0.1.0-rc.6\n升级方式:npm install -g @deepseek-ai/dsh\n升级后重启 dsh,即可使用最新功能。接入配置不变(base url 仍为 https://api.yomiapi.com/v1,密钥不变)。\n详细接入步骤见控制台「帮助文档 → DeepSeek Harness」。

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.