Before (OpenAI)
from openai import OpenAI
client = OpenAI(api_key="sk-your-key")
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Write a Python function"}]
)
After (DeepSeek via TokenHub)
from openai import OpenAI
client = OpenAI(base_url="https://t-hub.cc/v1", api_key="sk-your-token")
response = client.chat.completions.create(
model="deepseek-v3",
messages=[{"role": "user", "content": "Write a Python function"}]
)
Three changes. Zero refactoring. Same OpenAI SDK.
DeepSeek is 10x cheaper AND scores higher on coding benchmarks. The only catch is the Chinese phone requirement — TokenHub solves that.
Try it: https://t-hub.cc
Top comments (0)