Site descriptions, notices, and reviews are shown in the language in which they were submitted.
DragonAPI · 大模型接口中转 专注为开发者提供高性价比的大模型接口服务，一个账号打通主流模型，接口完全兼容 OpenAI 标准，改个 base_url 就能用，无需改动任何代码。 价格优势 按官方 0.03 倍率计费，1 刀站内额度约等于官方 33 刀的调用量。同样的预算，能跑出 30 倍以上的量。按量计费，用多少扣多少，无月租无套餐，不用为闲置额度买单。 稳定性 专线集群直连，多节点负载均衡，高并发不排队不掉线。原生接口直连，不做中间层转换，响应速度与官方无异。 透明可查 后台账单实时更新，每一笔调用的模型、token 消耗、扣费金额全程可追溯，消费明细一目了然，无隐形扣费。 充值即用 兑换码充值，秒到账，额度永久有效不清零。多档面值可选，按需充值。 广泛适配 VS Code、Cursor、Cherry Studio、Claude Code、Codex 原生客户端等主流开发工具即插即用，配套文档齐全，新手照着文档几分钟即可接入。 售后保障 长期运营，问题随时响应。接入遇到任何问题都可以直接联系，协助排查到能正常调用为止。
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
Opus 4.7
3 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
3 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
2 public records are listed; open the full page to review details as needed.
Price listing
Opus 4.6
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-kiro | claude-fable-5 | 输入 ¥1 / 输出 ¥5 / 缓存 ¥0.1 / 写入 ¥0 | -60% | — | — | — |
| claude-max | claude-fable-5 | 输入 ¥8 / 输出 ¥40 / 缓存 ¥0.8 / 写入 ¥0 | 0% | — | — | — |
| claude-max企业 | claude-fable-5 | 输入 ¥12 / 输出 ¥60 / 缓存 ¥1.2 / 写入 ¥0 | -25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4-8 | 输入 ¥0.5 / 输出 ¥2.5 / 缓存 ¥0.05 / 写入 ¥0.625 | -60% | — | — | — |
| claude-max | claude-opus-4-8 | 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 | 0% | — | — | — |
| claude-max企业 | claude-opus-4-8 | 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 | -25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4-7 | 输入 ¥0.5 / 输出 ¥2.5 / 缓存 ¥0.05 / 写入 ¥0.625 | -60% | — | — | — |
| claude-max | claude-opus-4-7 | 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 | 0% | — | — | — |
| claude-max企业 | claude-opus-4-7 | 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 | -25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-sonnet-5 | 输入 ¥0.2 / 输出 ¥1 / 缓存 ¥0.02 / 写入 ¥0 | -60% | — | — | — |
| claude-max | claude-sonnet-5 | 输入 ¥1.6 / 输出 ¥8 / 缓存 ¥0.16 / 写入 ¥0 | 0% | — | — | — |
| claude-max企业 | claude-sonnet-5 | 输入 ¥2.4 / 输出 ¥12 / 缓存 ¥0.24 / 写入 ¥0 | -25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gpt-特惠 | gpt-5.6-sol | 输入 ¥0.2625 / 输出 ¥2.1 / 缓存 ¥0.0262 / 写入 ¥0.3281 | -4.5% | — | — | — |
| gpt-plus | gpt-5.6-sol | 输入 ¥0.525 / 输出 ¥4.2 / 缓存 ¥0.0525 / 写入 ¥0.6563 | +5% | — | — | — |
| gpt-pro | gpt-5.6-sol | 输入 ¥0.9375 / 输出 ¥7.5 / 缓存 ¥0.0938 / 写入 ¥1.17 | -6.2% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gpt-特惠 | gpt-5.6-terra | 输入 ¥0.1313 / 输出 ¥1.05 / 缓存 ¥0.0131 / 写入 ¥0.1641 | +19% | — | — | — |
| gpt-plus | gpt-5.6-terra | 输入 ¥0.2625 / 输出 ¥2.1 / 缓存 ¥0.0262 / 写入 ¥0.3281 | +31% | — | — | — |
| gpt-pro | gpt-5.6-terra | 输入 ¥0.4688 / 输出 ¥3.75 / 缓存 ¥0.0469 / 写入 ¥0.5859 | +17% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| gpt-特惠 | gpt-5.5 | 输入 ¥0.35 / 输出 ¥2.1 / 缓存 ¥0.035 / 写入 ¥0.35 | +27% | — | — | — |
| gpt-plus | gpt-5.5 | 输入 ¥0.7 / 输出 ¥4.2 / 缓存 ¥0.07 / 写入 ¥0.7 | +40% | — | — | — |
| gpt-pro | gpt-5.5 | 输入 ¥1.25 / 输出 ¥7.5 / 缓存 ¥0.125 / 写入 ¥1.25 | +25% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 国模 | glm-5.2 | 输入 ¥3.2 / 输出 ¥11.2 / 缓存 ¥0.8 / 写入 ¥0 | +205% | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| 创浪云 | gpt-image-2 | ¥0.08 / 次 | - | — | — | — |
| image | gpt-image-2 | ¥0.08 / 次 | - | — | — | — |
| Channel | Provider model | Current price | Price trend | Uptime | Fake % | Latency |
|---|---|---|---|---|---|---|
| claude-kiro | claude-opus-4.6 | 输入 ¥0.5 / 输出 ¥2.5 / 缓存 ¥0.05 / 写入 ¥0 | 0% | — | — | — |
| claude-max | claude-opus-4-6 | 输入 ¥4 / 输出 ¥20 / 缓存 ¥0.4 / 写入 ¥5 | 0% | — | — | — |
| claude-max企业 | claude-opus-4-6 | 输入 ¥6 / 输出 ¥30 / 缓存 ¥0.6 / 写入 ¥7.5 | -25% | — | — | — |
🔧 8 月 26 日 14:03 服务中断说明与补偿 各位用户： 北京时间今天 14:03–14:14，本站 API 出现约 11 分钟不可用，表现为请求超时、Cloudflare 523 或直连地址无响应。主地址、国内加速地址、直连地址同时受影响，给各位的调用造成中断，非常抱歉。 【已完成的处理】 · 14:14 全部 IP 恢复，服务同步恢复；中断期间未接通的请求不会产生任何扣费 · 已将全部对外 IP 写入持久化网络配置并验证生效，今后系统升级或重启不会再复现 · 网络配置变更增加了校验与自动回补机制 【补偿】 兑换码：MAKEUP0826 · 每人 2 额度，限 50 人，先到先得 · 有效期至今晚 20:00（北京时间） · 每个账号限领 1 次，在「钱包 → 兑换码充值」中输入使用 再次为本次中断致歉。
进群发用户名，可以领0.5的试用额度 qq群：671892159
🎁 邀请返佣规则\n\n邀请好友注册，好友充值时你可获得返佣奖励：\n\n· 返佣比例：好友充值金额的 5%\n· 返佣次数：每位好友的前 3 次充值均可获得返佣\n· 适用范围：在线支付与兑换码充值均可返佣\n· 到账方式：返佣自动计入「邀请额度」，可在钱包页转入主余额（单次最低 $1）\n\n获取你的专属邀请链接：进入「钱包」页面复制，格式为\nhttps://newapi.dragon3api.com/sign-up?aff=你的邀请码\n\n好友通过该链接注册后自动绑定邀请关系，无需其他操作。
qq：671892159
【重要】旧域名停用通知：原接入地址 newapi.ldragon3.xyz 与 sub2api.ldragon3.xyz 已停止服务，请尽快将 API 地址（base url）更换为 https://newapi.dragon3api.com ，否则将无法继续调用。给您带来不便，敬请谅解。
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.