GPT-4 API Failing with “Connection error” on Paid CPU and Free tier CPU — Worked 2 Days Ago

Spaces
1

Issue Summary

Space: chunchu-08/LLM-Comparison-Hub
Hardware: Paid CPU Upgrade (8 vCPU, 32 GB RAM) Free tier CPU- It worked fine two days ago but now it is not working either on free tier CPU or Paid CPU
Model: gpt-4 via openai>=1.0.0 SDK
Error:

GPT-4 call works perfectly on local machine with same key:

from openai import OpenAI
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello GPT-4"}]
)
Claude and Gemini models work fine in the same Space

.env is loaded correctly using load_dotenv()

No IP restrictions set on OpenAI key

Logs just show Connection error. — no traceback

What I’ve Tried
Tested OPENAI_API_KEY locally — works

Added logging using test_openai_connection.py

Restarted Space and tested again

Confirmed Claude/Gemini give valid outputs

GPT-4 fails silently

My Questions
Has Hugging Face introduced outbound network restrictions to api.openai.com recently?

Does even paid CPU Space share outbound IP pools that are rate-limited by OpenAI?

Any recommended workaround?
1 Like
2

It seems that there is an SSL issue when using OpenAI from HF Spaces…:sweat_smile: @meganariley @pierric @Wauplin

/usr/local/lib/python3.10/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'api.openai.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
  warnings.warn(
Connected to https://api.openai.com, but the server returned an error. Status code: 421