Site descriptions, notices, and reviews are shown in the language in which they were submitted.
🔥 Claude 2.5 折 / GPT 1.5 折 · 原生协议直连官方 API OpenAI 最低 · 0.06折 Fable 5 最低 · 0.06折 国产模型齐全 按量计费，价格透明，用多少扣多少。报价均为「输入/输出 每百万 token」 支持模型 Anthropic Fable 5 · Opus 5 · Sonnet 5 · Opus 4.8 · Opus 4.7 · Sonnet 4.6 OpenAI GPT-5.6 Sol · Terra · Luna · GPT-5.5 · GPT-5.4 针对Workbuddy模型单独开发一键CMD配置 开箱即用 龙虾 OpenClaw · 爱马仕 Hermes Agent · Claude Code CLI · Codex Desktop · Codex CLI 改一个 base_url 即可接入，无需改代码。
Price listing
Opus 4.8
2 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.7
2 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Sol
10 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Terra
10 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.5
6 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.6
2 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 |
|---|---|---|---|---|---|---|
| 【Kiro】-专线Kiro-高缓存-需自测 | claude-opus-4-8 | 输入 ¥0.43 / 输出 ¥2.15 / 缓存 ¥0.043 / 写入 ¥0.5375 | 0% | — | — | — |
| 【Kiro】-满血Kiro-高缓存-满血满智 | claude-opus-4-8 | 输入 ¥1.03 / 输出 ¥5.15 / 缓存 ¥0.103 / 写入 ¥1.29 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【Kiro】-专线Kiro-高缓存-需自测 | claude-opus-4-7 | 输入 ¥0.43 / 输出 ¥2.15 / 缓存 ¥0.043 / 写入 ¥0.5375 | 0% | — | — | — |
| 【Kiro】-满血Kiro-高缓存-满血满智 | claude-opus-4-7 | 输入 ¥1.03 / 输出 ¥5.15 / 缓存 ¥0.103 / 写入 ¥1.29 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【超级特惠】-满血GPT-PROMax-随时拉闸 | gpt-5.6-sol | 输入 ¥0.345 / 输出 ¥2.07 / 缓存 ¥0.0345 / 写入 ¥0.4313 | 0% | — | — | — |
| 【外模号池2】-GPT-PLUS-福利分组-009 | gpt-5.6-sol | 输入 ¥0.495 / 输出 ¥2.97 / 缓存 ¥0.0495 / 写入 ¥0.6188 | 0% | — | — | — |
| 【超级特惠】-GPTplus-稳定混合组 | gpt-5.6-sol | 输入 ¥0.5 / 输出 ¥3 / 缓存 ¥0.05 / 写入 ¥0.625 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【超级特惠】-满血GPT-PROMax-随时拉闸 | gpt-5.6-terra | 输入 ¥0.138 / 输出 ¥0.828 / 缓存 ¥0.0138 / 写入 ¥0.1725 | 0% | — | — | — |
| 【外模号池2】-GPT-PLUS-福利分组-009 | gpt-5.6-terra | 输入 ¥0.198 / 输出 ¥1.19 / 缓存 ¥0.0198 / 写入 ¥0.2475 | 0% | — | — | — |
| 【超级特惠】-GPTplus-稳定混合组 | gpt-5.6-terra | 输入 ¥0.2 / 输出 ¥1.2 / 缓存 ¥0.02 / 写入 ¥0.25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【超级特惠】-满血GPT-5.5-只有5.5可用！ | gpt-5.5 | 输入 ¥0.23 / 输出 ¥1.38 / 缓存 ¥0.023 / 写入 ¥0 | 0% | — | — | — |
| 【超级特惠】-GPTplus-稳定混合组 | gpt-5.5 | 输入 ¥0.5 / 输出 ¥3 / 缓存 ¥0.05 / 写入 ¥0 | 0% | — | — | — |
| 【备用特惠】-满血GPT-PLUS-独立号池 | gpt-5.5 | 输入 ¥0.618 / 输出 ¥3.71 / 缓存 ¥0.0618 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 【Kiro】-专线Kiro-高缓存-需自测 | claude-opus-4-6 | 输入 ¥0.43 / 输出 ¥2.15 / 缓存 ¥0.043 / 写入 ¥0.645 | 0% | — | — | — |
| 【Kiro】-满血Kiro-高缓存-满血满智 | claude-opus-4-6 | 输入 ¥1.03 / 输出 ¥5.15 / 缓存 ¥0.103 / 写入 ¥1.54 | 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.