High-performance LLM API relay — powered by DeepSeek, priced at 90% of official rates
curl https://aiconnections.top/v1/chat/completions \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello!"}]
}'
| Base URL | https://aiconnections.top/v1 |
| Auth | Authorization: Bearer YOUR_TOKEN |
| Format | OpenAI-compatible (chat completions) |
| Streaming | Supported ("stream": true) |
DeepSeek V4 series. All prices include a 5-10% service fee over direct API costs — no hidden charges, no minimum spend.
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
deepseek-v4-flash | $0.154 | $0.308 | 1M |
deepseek-v4-pro | $0.455 | $0.91 | 1M |
600 requests / minute per IP address. Exceeding returns HTTP 429 Too Many Requests. Contact us if you need higher limits.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_TOKEN",
base_url="https://aiconnections.top/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
const response = await fetch("https://aiconnections.top/v1/chat/completions", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_TOKEN",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "deepseek-v4-flash",
messages: [{ role: "user", content: "Hello!" }]
})
});
const data = await response.json();
console.log(data.choices[0].message.content);
Q: What's the difference from DeepSeek official API?
Same models, same quality. We charge 90% of official rates. No billing setup needed — just top up and use.
Q: Does credit expire?
No. Your balance never expires.
Q: Which OpenAI features are supported?
Chat completions, streaming, function calling, JSON mode — all standard features.
Q: Need more quota or custom plans?
Contact us. We're happy to set up custom pricing for high-volume users.