OpenAI restricts access from mainland China and increasingly gates advanced models behind organization verification (ID + face). API Models proxies the GPT family — chat (GPT-5), images (gpt-image-2) and more — through a China-reachable, OpenAI-compatible endpoint. Point your SDK at our base URL and it just works.
Because the endpoint is OpenAI-compatible, the openai-python / openai-node SDKs, Cursor, Cline and other tools work unchanged — just change base_url and key. Pay-as-you-go from $10, $0.5 free on signup.
cURL
curl https://apimodels.app/api/v1/chat/completions \
-H "Authorization: Bearer $APIMODELS_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "gpt-5.1", "messages": [{"role":"user","content":"Hi"}] }'Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_KEY", base_url="https://apimodels.app/api/v1")
print(client.chat.completions.create(
model="gpt-5.1",
messages=[{"role": "user", "content": "Hi"}],
).choices[0].message.content)No. You never touch OpenAI’s console — we handle upstream access. No ID or face verification.
Yes — gpt-image-2 / lite / beta are available at a flat $0.03/image. See the image docs.
Yes. Set base_url to https://apimodels.app/api/v1 and use your API Models key — no other changes.