OpenAI-compatible DeepSeek API access. Change the base_url, keep your code. No registration queue. No foreign payment hassle.
from openai import OpenAI
client = OpenAI(
base_url="https://modelrelayapis.cc/v1",
api_key="sk-gateway-YOUR-KEY",
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role":"user","content":"Hello!"}],
)
print(response.choices[0].message.content)| Model | Speed | Coding | Reasoning | Cost | Best For |
|---|---|---|---|---|---|
deepseek-v4-flash |
★★★★★ | ★★★ | ★★★ | Low | Chat, content, roleplay, high-volume |
deepseek-v4-pro |
★★★ | ★★★★★ | ★★★★★ | Medium | Complex coding, reasoning, research |
Based on real DeepSeek token pricing: input cache-hit $0.014/M, cache-miss $0.14/M, output $0.28/M (flash). Your budget decreases with each request.
HTTP 402 is returned and your key becomes exhausted. Buy a new package to continue.
Yes. 30 or 60 RPM per key depending on your plan. Exceeding returns HTTP 429.
Yes. Set base_url to our endpoint and pass your gateway key. Zero code changes needed.