Calling the API with Python
After reading this guide, you can call our models using Python's official openai library. Our API is OpenAI-compatible, so you can use the official library directly.
Installation
pip install openai
Code
from openai import OpenAI
client = OpenAI(
api_key="sk-xxxxxxxx",
base_url="https://api.tvtapi.com/v1",
)
response = client.chat.completions.create(
model="your-model-name", # copy from model marketplace
messages=[
{"role": "user", "content": "Hello"}
],
)
print(response.choices[0].message.content)
Two substitutions:
sk-xxxxxxxx→ your API Keyyour-model-name→ a model name copied from the model marketplace
Streaming Output
stream = client.chat.completions.create(
model="your-model-name",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
Troubleshooting
- 401: wrong Key — see Error Code Reference.
Connection error: check your network and Base URL.