Yun API is a high-speed, stable, and high-concurrency API relay service based on official APIs, offering access to over 100 AI models including text, image, and video generation.
哈基米API站 offers a unified API gateway for large language models with competitive pricing and stable service.
实测速度更快
30 天可用性更高
模型覆盖更广
323
0
$0.930/M
119 tok/s
9990%
公告
warning2026/6/13
Dear User,
DuckCoding is not available in Mainland China and does not support registration or use by users located there; it is intended solely for regions outside Mainland China.
You agree not to use any VPN, proxy, or other means to bypass these restrictions. Any violation lets us immediately suspend or terminate your account without refund.
For inquiries or refunds, contact [email protected] with your account and billing details, or submit a ticket.
Recharges are calculated on a one-to-one ratio (1 RMB is exchangeable for 1 on-site credit).
The refund handling fee is set at 5%, calculated proportionally. There are no handling fees for balance transfers or other transfer-related operations.
Should you have any inquiries concerning enterprise cooperation or large-sum recharges, please do not hesitate to contact us via email at [email protected] or submit a ticket.
FAQ
Invoice-related Matters
For matters concerning invoicing and corporate payment transactions, please contact us in advance via email at [email protected] or submit a support ticket.
Invoice Type: Corporate, Electronic General Invoice/Electronic Value-Added Tax Invoice for Technical Service Fees.
Invoicing will be finalized within 1-3 working days.
Refund Policy
This website facilitates refunds. To apply for a refund, please submit your payment order and contact us at [email protected] or submit a support ticket.
The refund amount will be calculated proportionally based on the actual usage, and a 5% handling fee will be deducted. The refund process will be completed within 1-3 business days.
注释
健康检查: 统计范围:72 小时图表和近期可用率只衡量 API 连通性,每个柱形汇总一小时内的检查结果。 检查目标:LMSpeed 会优先尝试已配置的健康检查 URL 和 Provider 状态 URL,再尝试从已知 API Host 与近期测速 Base URL 推导出的 API 端点;只有官网地址本身明显是 API 地址时才会作为候选。 探测步骤:每个候选地址依次进行 DNS 解析、TCP 连接、HTTPS 的 TLS 握手,以及自动跟随重定向的 HTTP HEAD 请求;找到首个可达地址后停止尝试。 可达标准:所有必需的网络步骤都必须成功。除被归类为拦截的状态外,低于 500 的 HTTP 响应均视为可达;其中 401 表示需要鉴权,但也证明 API 端点已响应。 拦截结果:HTTP 403、429、521、525、530,以及识别出的 WAF 或 Cloudflare 挑战会标记为“被拦截”,不计入可用率,因为 LMSpeed 无法据此判断 API 本身是否宕机。 模型可用性:配置专用测试 Key 后,LMSpeed 会向推导出的 /models 端点发送带鉴权的 GET 请求,并将返回的模型 ID 与该 Provider 收录的模型进行比对。逐模型结果显示在“模型与价格”中,不计入 Provider 连通性百分比。 超时限制:TCP 连接、TLS 握手、HTTP 连通性请求和模型请求分别使用 20 秒超时;尝试多个候选地址时,整轮检查可能超过 20 秒。 检查频率:后台 Worker 默认每 5 分钟检查一次所有 Provider;72 小时图表会将这些采样汇总为小时柱形,运营方也可以调整调度。 限制说明:自动抽样结果不构成 SLA,也不能保证账户额度、所有模型、所有地区或实际补全请求始终成功;作出运维决策前请同时查看 Provider 官方状态页。
Domain Rating 数据来自 Ahrefs。它是基于外链估算的 0–100 域名强度信号,不代表 API 速度或可用性。