Fully OpenAI Compatible
Just change base_url and api_key to seamlessly connect any OpenAI SDK or HTTP client without modifying a single line of business code.
Access DeepSeek, Zhipu, Qwen, Doubao and more in one place. High-availability relay, real-time billing, developer-friendly.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://www.ciyuano.com/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)16+
Available Models
5
Upstream Providers
99.9%
Service Uptime
<200ms
Avg Latency
Covering DeepSeek, Zhipu, Qwen, Doubao and more, constantly expanding
agnes-2.0-flashagnes-image-2.0-flashagnes-image-2.1-flashagnes-video-v2.0agnes-2.5-flashagnes-2.5-proOne-stop AI API solution, integrating LLMs is as easy as breathing
Just change base_url and api_key to seamlessly connect any OpenAI SDK or HTTP client without modifying a single line of business code.
Support DeepSeek, GLM, Qwen and more with intelligent load balancing and automatic failover.
Channel health checks, key pool rotation, automatic retries ensuring 99.9% API uptime.
Precise per-request token billing with visual dashboard for real-time usage and cost monitoring.
Full SSE streaming support with real-time reasoning model thinking process, native-like experience.
Independent API Key system, balance control, model whitelist, request log audit.
No code changes needed, migrate instantly
Register
Free registration with instant trial credits
Create API Key
Generate keys with one click in the dashboard
Integrate
Change base_url and start calling
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://www.ciyuano.com/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user",
"content": "Hello!"}]
)No monthly fees. Pay only for what you use. Free credits on registration.
| Provider | Model | Input | Output | Context |
|---|---|---|---|---|
| agnes-2.0-flash | ¥0 | ¥0 | 125K | |
| agnes-image-2.0-flash | ¥0 | ¥0 | 125K | |
| whisper-1 | ¥0.006 | ¥0 | 0K | |
| tts-1 | ¥0.015 | ¥0 | 0K | |
| tts-1-hd | ¥0.03 | ¥0 | 0K | |
| mimo-v2.5 | ¥1 | ¥2 | 1024K | |
| agnes-image-2.1-flash | ¥2 | ¥8 | 125K | |
| agnes-video-v2.0 | ¥2 | ¥8 | 125K |
One API key, all models. No need to manage multiple vendor accounts.
| Feature | Ciyuano | Direct API | Other Relay |
|---|---|---|---|
| OpenAI Compatible | |||
| Multi-model Support | — | ||
| Auto Failover | — | — | |
| Key Pool Rotation | ✗ | — | |
| Smart Routing | ✗ | ✗ | |
| Usage Dashboard | ✗ | ✗ | |
| Free Trial Credits | ✗ | ✗ |
Tech sharing and product updates

不管你是应届生还是职场转行,AI 都能帮你把简历从"凑合能用"变成"眼前一亮"。本文用五个步骤,手把手教你用 AI 生成、修改、优化出一份真正能拿面试的专业简历。

还在打字到手指发酸?还在为会议记录发愁?AI 语音转文字技术已经非常成熟,学会使用它,可以帮你把说话直接变成文字,效率提升数倍。本文将手把手教你选择工具、完成转写、导出使用,让 AI 成为你的打字替身。

明明 AI 功能强大,但每次提问得到的回答都差强人意?其实问题往往不在 AI,而在于你提问的方式。本文用最直观的方式教你 7 个让 AI 回答更准确的实用技巧,包括四要素公式、精准提问、背景信息、拆分任务、追问迭代、万能模板和常见错误,小白也能立即上手。
Register for free trial credits, complete integration in 5 minutes. Supports DeepSeek, GLM, Qwen and all major models.