Lightning-Fast AI API
at 70% Less

OpenAI-compatible inference API powered by DeepSeek, Qwen, and GLM. Same quality, fraction of the cost. Deploy in 30 seconds.

Get Started Free → Read the Docs
OpenAI Compatible No Credit Card 99.9% Uptime Global CDN

$0.60

Per 1M input tokens

<200ms

Average latency

10B+

Tokens served

4

Production models

quickstart.py
from openai import OpenAI
client = OpenAI(
  base_url="https://ziyeapi.com/v1",
  api_key="sk-...your-key"
)
response = client.chat.completions.create(
  model="deepseek-v3",
  messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
# ✨ Response in 186ms — $0.00012

How It Works

Get Started in 3 Steps

From signup to your first API call in under 2 minutes.

STEP 1

Create Account

Sign up in 10 seconds. No credit card required. Get 100K free tokens instantly.

STEP 2

Get API Key

Generate your API key from the dashboard. One key for all models.

STEP 3

Start Building

Drop in any OpenAI SDK. Just change the base_url. That's it — you're live.

Models

State-of-the-Art AI Models

Access the most powerful open-source models through a single, unified API.

🌊 DeepSeek-V3
671B Mixture-of-Experts. GPT-4 class performance at 1/30th the cost.
$0.27/1M in671B MoETop Tier
🧠 DeepSeek-R1
Advanced reasoning model. Excels at math, code, and logic.
$0.55/1M in671B MoEReasoning
⚡ Qwen 2.5 7B
Lightweight & fast. Perfect for high-volume tasks.
$0.14/1M in7BFast
🚀 GLM-4 Flash
Zhipu AI's fastest model. Free tier available.
FREE9BFree Tier

Pricing

Simple, Transparent Pricing

No hidden fees. Pay for what you use.

🌱 Starter

Free
  • 100K tokens/month
  • 3 models
  • Community support
  • 10 RPM

🚀 Pro

$29/mo
  • 5M tokens/month
  • All models
  • Priority support
  • 99.9% uptime SLA
  • 100 RPM

🏢 Enterprise

$99/mo
  • 50M tokens/month
  • All models + early access
  • Dedicated support
  • Custom rate limits
  • SLA guarantee

FAQ

Common Questions

How is this different from OpenAI?
We use the same OpenAI-compatible API format, but run on leading open-source models like DeepSeek-V3. GPT-4 class performance at 70% lower cost. Just swap the base URL and API key.
Is the API OpenAI-compatible?
Yes! Any library that works with OpenAI (python-openai, langchain, etc.) works with ZiYe out of the box.
What about data privacy?
We do not store your prompts or responses. All requests are processed in real-time and not logged.
What payment methods?
We accept credit cards (Visa, Mastercard, Amex) via Stripe. Enterprise plans can pay via wire transfer.

Welcome Back

Sign in to your ZiYeAPI account

Forgot Password?
Don't have an account? Sign Up

Reset Password

Enter your username to receive a password reset link

← Back to Sign In

Account

Change Password

Update your account password.

← Back to Dashboard

Create Account

Get started with 100K free tokens

Already have an account? Sign In

Dashboard

Welcome, User

Manage your API keys and monitor usage.

💰 Account Balance

0
tokens remaining
⚡ Recharge

API Endpoint

-

Used Quota

0
tokens consumed

Remaining Quota

0
tokens available

Status

● Active

API Keys

Your API Keys

No API keys yet. Click "New Key" to create one.
Playground Recharge API Docs Change Password Logout

Billing

Recharge

Add tokens to your account. More tokens = more API calls.

Current Balance

0
tokens remaining

Select Amount

$5
500K tokens
$10
2M tokens
+10% bonus
$29
5M tokens
+20% bonus
$99
20M tokens
+30% bonus
← Back to Dashboard

Documentation

Start in 30 Seconds

Drop-in replacement for OpenAI. Just change the base URL and API key.

Base URL: http://47.82.164.254:3000/v1

Python
import openai

client = openai.OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="http://47.82.164.254:3000/v1"
)
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
cURL
curl http://47.82.164.254:3000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -d '{"model":"deepseek-ai/DeepSeek-V3","messages":[{"role":"user","content":"Hello!"}]}'
JavaScript
const resp = await fetch("http://47.82.164.254:3000/v1/chat/completions", {
  method: "POST",
  headers: { "Content-Type": "application/json", "Authorization": "Bearer sk-YOUR_API_KEY" },
  body: JSON.stringify({ model:"deepseek-ai/DeepSeek-V3", messages:[{role:"user",content:"Hello!"}] })
});
const data = await resp.json();
console.log(data.choices[0].message.content);
Node.js SDK
import OpenAI from 'openai';
const client = new OpenAI({ apiKey:"sk-YOUR_API_KEY", baseURL:"http://47.82.164.254:3000/v1" });
const r = await client.chat.completions.create({ model:"deepseek-ai/DeepSeek-V3", messages:[{role:"user",content:"Hello!"}] });
console.log(r.choices[0].message.content);

Playground

Try It Now

Send a message and see the response in real time.

← Dashboard

Chat

Select a model and start chatting ↓