Site descriptions, notices, and reviews are shown in the language in which they were submitted.
MiKu 是一个专注于 Codex / Claude Code / 主流大模型 API 的高稳定分发平台。 通过自研网关与资源调度体系，我们为用户提供： - 更稳定的调用体验 - 更低的使用成本 - 更清晰可控的计费方式 适用人群 - AI 产品开发者 / 独立开发者 - 需要长期稳定调用 Claude / Codex 的团队 - 自动化 / Agent / Coding 场景用户 - 对成本敏感、需要精细化控制 token 的用户
Price listing
Fable 5
2 public records are listed; open the full page to review details as needed.
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
Sonnet 5
2 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Sol
2 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.6 Terra
2 public records are listed; open the full page to review details as needed.
Price listing
GPT 5.5
2 public records are listed; open the full page to review details as needed.
Price listing
GPT Image 2
5 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逆向,支持4.7 | claude-fable-5 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥6.25 | 0% | — | — | — |
| Claude-Max逆向 | claude-fable-5 | 输入 ¥10 / 输出 ¥50 / 缓存 ¥1 / 写入 ¥12.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro逆向,支持4.7 | claude-opus-4-8 | 输入 ¥2.5 / 输出 ¥12.5 / 缓存 ¥0.25 / 写入 ¥3.13 | 0% | — | — | — |
| Claude-Max逆向 | claude-opus-4-8 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥6.25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro逆向,支持4.7 | claude-opus-4-7 | 输入 ¥2.5 / 输出 ¥12.5 / 缓存 ¥0.25 / 写入 ¥3.13 | 0% | — | — | — |
| Claude-Max逆向 | claude-opus-4-7 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥6.25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro逆向,支持4.7 | claude-sonnet-5 | 输入 ¥1 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥1.25 | 0% | — | — | — |
| Claude-Max逆向 | claude-sonnet-5 | 输入 ¥2 / 输出 ¥10 / 缓存 ¥0.2 / 写入 ¥2.5 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| GPT | gpt-5.6-sol | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥1.88 | 0% | — | — | — |
| gpt-image-2-支持4k(选这个就行) | gpt-5.6-sol | 输入 ¥3.75 / 输出 ¥22.5 / 缓存 ¥0.375 / 写入 ¥4.69 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| GPT | gpt-5.6-terra | 输入 ¥0.6 / 输出 ¥3.6 / 缓存 ¥0.06 / 写入 ¥0.75 | 0% | — | — | — |
| gpt-image-2-支持4k(选这个就行) | 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 |
|---|---|---|---|---|---|---|
| GPT | gpt-5.5 | 输入 ¥1.5 / 输出 ¥9 / 缓存 ¥0.15 / 写入 ¥0 | 0% | — | — | — |
| gpt-image-2-支持4k(选这个就行) | gpt-5.5 | 输入 ¥3.75 / 输出 ¥22.5 / 缓存 ¥0.375 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| GPT | gpt-image-2 | ¥0.099 / 张 | - | — | — | — |
| gpt-image-2(官key) | gpt-image-2 | ¥0.1 / 张 | - | — | — | — |
| gpt-image-2官key | gpt-image-2 | ¥0.1 / 张 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro逆向,支持4.7 | claude-opus-4-6 | 输入 ¥2.5 / 输出 ¥12.5 / 缓存 ¥0.25 / 写入 ¥3.13 | 0% | — | — | — |
| Claude-Max逆向 | claude-opus-4-6 | 输入 ¥5 / 输出 ¥25 / 缓存 ¥0.5 / 写入 ¥6.25 | 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.