Site descriptions, notices, and reviews are shown in the language in which they were submitted.
Tuturu（https://api.tuturu.dev）是 2026 年 6 月开业的多模型 API 中转，个人维护。主要给 Claude Code、Gemini CLI、Codex 用，原生 /v1/messages、广场按真实探测显示健康信息、空补全不乱扣。支持多种境内境外支付方式。渠道从逆向的kiro，订阅套餐到官方AWS-Bedrock，Azure，Vertex全覆盖。售后走邮箱 [email protected]、Telegram、QQ 群 1026293124，出问题能对到请求 ID，并且按需求修改传输格式，过滤参数等等。
Price listing
Fable 5
5 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.8
10 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.7
10 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
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 5.5
3 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
10 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 |
|---|---|---|---|---|---|---|
| claude-kiro稳定 | claude-fable-5 | 输入 ¥4.5 / 输出 ¥22.5 / 缓存 ¥0.45 / 写入 ¥5.63 | -25% | — | — | — |
| aws-q逆 | claude-fable-5 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥10 | 0% | — | — | — |
| ccmax专用 | claude-fable-5 | 输入 ¥9 / 输出 ¥45 / 缓存 ¥0.9 / 写入 ¥11.25 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro高缓 | claude-opus-4-8 | 输入 ¥1 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥1.25 | 0% | — | — | — |
| claude-kiro稳定 | claude-opus-4-8 | 输入 ¥2.25 / 输出 ¥11.25 / 缓存 ¥0.225 / 写入 ¥2.81 | -25% | — | — | — |
| cursor逆向 | claude-opus-4-8 | 输入 ¥3.75 / 输出 ¥18.75 / 缓存 ¥0.375 / 写入 ¥4.69 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro高缓 | claude-opus-4-7 | 输入 ¥1 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥1.25 | 0% | — | — | — |
| claude-kiro稳定 | claude-opus-4-7 | 输入 ¥2.25 / 输出 ¥11.25 / 缓存 ¥0.225 / 写入 ¥2.81 | -25% | — | — | — |
| cursor逆向 | claude-opus-4-7 | 输入 ¥3.75 / 输出 ¥18.75 / 缓存 ¥0.375 / 写入 ¥4.69 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro高缓 | claude-sonnet-5 | 输入 ¥0.4 / 输出 ¥2 / 缓存 ¥0.04 / 写入 ¥0.5 | 0% | — | — | — |
| claude-kiro稳定 | claude-sonnet-5 | 输入 ¥0.9 / 输出 ¥4.5 / 缓存 ¥0.09 / 写入 ¥1.13 | -25% | — | — | — |
| aws-q逆 | claude-sonnet-5 | 输入 ¥1.6 / 输出 ¥8 / 缓存 ¥0.16 / 写入 ¥2 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| codex | gpt-5.6-sol | 输入 ¥1 / 输出 ¥8 / 缓存 ¥0.1 / 写入 ¥1.25 | -17% | — | — | — |
| pro | gpt-5.6-sol | 输入 ¥2.25 / 输出 ¥18 / 缓存 ¥0.225 / 写入 ¥2.81 | 0% | — | — | — |
| pro不降智 | gpt-5.6-sol | 输入 ¥2.75 / 输出 ¥22 / 缓存 ¥0.275 / 写入 ¥3.44 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| codex | gpt-5.6-terra | 输入 ¥0.5 / 输出 ¥4 / 缓存 ¥0.05 / 写入 ¥0.625 | -17% | — | — | — |
| pro | gpt-5.6-terra | 输入 ¥1.13 / 输出 ¥9 / 缓存 ¥0.1125 / 写入 ¥1.41 | 0% | — | — | — |
| pro不降智 | gpt-5.6-terra | 输入 ¥1.38 / 输出 ¥11 / 缓存 ¥0.1375 / 写入 ¥1.72 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| codex | gpt-5.5 | 输入 ¥1 / 输出 ¥6 / 缓存 ¥0.1 / 写入 ¥0 | -17% | — | — | — |
| pro | gpt-5.5 | 输入 ¥2.25 / 输出 ¥13.5 / 缓存 ¥0.225 / 写入 ¥0 | 0% | — | — | — |
| Azure | gpt-5.5 | 输入 ¥14 / 输出 ¥84 / 缓存 ¥1.4 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 国产 | glm-5.2 | 输入 ¥5.6 / 输出 ¥19.6 / 缓存 ¥1.4 / 写入 ¥0 | +7.7% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| image | gpt-image-2 | ¥0.2 / 次 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| kiro高缓 | claude-opus-4-6 | 输入 ¥1 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥1.25 | 0% | — | — | — |
| claude-kiro稳定 | claude-opus-4-6 | 输入 ¥2.25 / 输出 ¥11.25 / 缓存 ¥0.225 / 写入 ¥2.81 | -25% | — | — | — |
| cursor逆向 | claude-opus-4-6 | 输入 ¥3.75 / 输出 ¥18.75 / 缓存 ¥0.375 / 写入 ¥4.69 | 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.