Site descriptions, notices, and reviews are shown in the language in which they were submitted.
奇异果AI：让对话更有趣 💕 💝专业稳定的技术支持，服务正常运行，7×24小时稳定服务 为什么选择奇异果AI？：专业稳定的智能对话API服务 1.极速响应，毫秒级响应时间流畅对话不间断 2.稳定可靠，双节点保障99.9%服务可用性 3.专业服务，多平台兼容优化贴心技术支持
Price listing
Fable 5
4 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.8
4 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.7
4 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
4 public records are listed; open the full page to review details as needed.
Price listing
GPT Image 2
3 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.6
4 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 |
|---|---|---|---|---|---|---|
| 胭脂莓 | claude-fable-5 | 输入 ¥16 / 输出 ¥80 / 缓存 ¥1.6 / 写入 ¥20 | 0% | — | — | — |
| claude code专用 | claude-fable-5 | 输入 ¥16 / 输出 ¥80 / 缓存 ¥1.6 / 写入 ¥20 | 0% | — | — | — |
| 龙晴荔 | claude-fable-5 | 输入 ¥24 / 输出 ¥120 / 缓存 ¥2.4 / 写入 ¥30 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 胭脂莓 | claude-opus-4-8 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| claude code专用 | claude-opus-4-8 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| 龙晴荔 | claude-opus-4-8 | 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 胭脂莓 | claude-opus-4-7-thinking | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| claude code专用 | claude-opus-4-7-thinking | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| 龙晴荔 | claude-opus-4-7-thinking | 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥15 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 胭脂莓 | claude-sonnet-5 | 输入 ¥4.8 / 输出 ¥24 / 缓存 ¥0.48 / 写入 ¥6 | 0% | — | — | — |
| claude code专用 | claude-sonnet-5 | 输入 ¥4.8 / 输出 ¥24 / 缓存 ¥0.48 / 写入 ¥6 | 0% | — | — | — |
| 龙晴荔 | claude-sonnet-5 | 输入 ¥7.2 / 输出 ¥36 / 缓存 ¥0.72 / 写入 ¥9 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 雪椰芯 | gpt-5.6-sol | 输入 ¥3 / 输出 ¥18 / 缓存 ¥0.3 / 写入 ¥3.75 | 0% | — | — | — |
| codex专用 | gpt-5.6-sol | 输入 ¥3 / 输出 ¥18 / 缓存 ¥0.3 / 写入 ¥3.75 | 0% | — | — | — |
| default | gpt-5.6-sol | 输入 ¥3 / 输出 ¥18 / 缓存 ¥0.3 / 写入 ¥3.75 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 雪椰芯 | gpt-5.6-terra | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥1.88 | 0% | — | — | — |
| codex专用 | gpt-5.6-terra | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥1.88 | 0% | — | — | — |
| default | gpt-5.6-terra | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥1.88 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 雪椰芯 | gpt-image-2 | ¥0.08 / 次 | - | — | — | — |
| codex专用 | gpt-image-2 | ¥0.08 / 次 | - | — | — | — |
| default | gpt-image-2 | ¥0.08 / 次 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 胭脂莓 | claude-opus-4-6 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| claude code专用 | claude-opus-4-6 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| 龙晴荔 | claude-opus-4-6 | 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥15 | 0% | — | — | — |
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.