OpenAI-compatible API gateway to DeepSeek V4-Pro and V4-Flash. Drop-in replacement. No code rewrite needed.
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
baseURL: 'https://hnqyai.com/v1' // Just change this line!
});
// Everything else stays the same
const response = await client.chat.completions.create({
model: 'deepseek-v4-flash',
messages: [{ role: 'user', content: 'Hello!' }]
});Direct access to DeepSeek V4 models through a single, unified API
Simple, powerful, and cost-effective AI infrastructure
V4-Flash input at $0.22/M tokens vs GPT-4o's $2.50/M. V4-Pro output at $5.60/M vs GPT-4o's $10.00/M. Same quality, fraction of the cost.
Change one line: base_url. Works with all OpenAI SDKs, LangChain, LlamaIndex, and any OpenAI-compatible tool. Also supports gpt-4o and gpt-4o-mini aliases.
Both V4-Pro and V4-Flash support DeepSeek's thinking mode for complex reasoning. Get deeper analysis when you need it, skip it when you don't.
Just change the base URL. Everything else stays the same.
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://hnqyai.com/v1" # Just change this line!
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Pay only for what you use. No hidden fees, no minimums.
| Model | Input | Output | Context |
|---|---|---|---|
| GPT-4o | $2.50/M | $10.00/M | 128K |
| DeepSeek-V4-Pro 44% OFF output | $2.80/M | $5.60/M | 1M |
| DeepSeek-V4-Flash 91% OFF input | $0.22/M | $0.44/M | 1M |