Site descriptions, notices, and reviews are shown in the language in which they were submitted.
星桥AI是面向个人开发者、AI爱好者和中小团队的大模型API聚合接入平台，致力于让模型调用更简单、更透明。平台提供多种主流模型与统一接口，适用于AI对话、编程辅助、内容创作、应用开发和自动化工作流等场景，具体可用模型以站内列表为准。用户可在线查看模型价格、接口类型及近期可用性，按实际用量计费，余额、账单和调用记录清晰可查。我们持续优化线路质量与调用体验，遇到接入、配置或使用问题，可通过客服QQ和用户交流群获得协助。价格透明，建议先小额体验，再根据实际需求选择合适的模型与线路。用户交流群：1076113993。
Price listing
Fable 5
3 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
Sonnet 5
2 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
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
3 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高缓 | claude-fable-5 | 输入 ¥10.5 / 输出 ¥10.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Kiro-Claude-满血 | claude-fable-5 | 输入 ¥24.75 / 输出 ¥24.75 / 缓存 ¥0 / 写入 ¥0 | -5.7% | — | — | — |
| Claude官key | claude-fable-5 | 输入 ¥97.5 / 输出 ¥97.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Claude高缓 | claude-opus-4-8 | 输入 ¥10.5 / 输出 ¥52.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Kiro-Claude-满血 | claude-opus-4-8 | 输入 ¥24.75 / 输出 ¥123.75 / 缓存 ¥0 / 写入 ¥0 | -5.7% | — | — | — |
| Claude官key | claude-opus-4-8 | 输入 ¥97.5 / 输出 ¥487.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| Kiro-Claude-满血 | claude-sonnet-5 | 输入 ¥24.75 / 输出 ¥24.75 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Claude官key | claude-sonnet-5 | 输入 ¥97.5 / 输出 ¥97.5 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| default | gpt-5.6-sol | 输入 ¥4.88 / 输出 ¥29.25 / 缓存 ¥0 / 写入 ¥0 | +1285% | — | — | — |
| GPT-并发分组 | gpt-5.6-sol | 输入 ¥10.88 / 输出 ¥65.25 / 缓存 ¥0 / 写入 ¥0 | +1689% | — | — | — |
| GPT-Pro专线-不降智 | gpt-5.6-sol | 输入 ¥13.5 / 输出 ¥81 / 缓存 ¥0 / 写入 ¥0 | +1775% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| GPT-并发分组 | gpt-5.6-terra | 输入 ¥10.88 / 输出 ¥65.25 / 缓存 ¥0 / 写入 ¥0 | +3477% | — | — | — |
| GPT-Pro专线-不降智 | gpt-5.6-terra | 输入 ¥13.5 / 输出 ¥81 / 缓存 ¥0 / 写入 ¥0 | +3650% | — | — | — |
| GPT-企业分组 | gpt-5.6-terra | 输入 ¥21 / 输出 ¥126 / 缓存 ¥0 / 写入 ¥0 | +3650% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 海外自部署国模ds/glm/kimi/qwen | glm-5.2 | 输入 ¥26.25 / 输出 ¥26.25 / 缓存 ¥0 / 写入 ¥0 | 0% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| GPT-image2生图 | gpt-image-2 | ¥0.09 / 次 | - | — | — | — |
| GPT-Pro专线-不降智 | gpt-image-2 | ¥0.09 / 次 | - | — | — | — |
| GPT-企业分组 | gpt-image-2 | ¥0.14 / 次 | - | — | — | — |
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.