The official openai Python package is the easiest way to call any OpenAI-compatible API from Python.
Client setup
import os
from openai import OpenAI
client = OpenAI(
base_url="https://devsaio.lol/v1",
api_key=os.environ["DEVSAIO_API_KEY"],
timeout=120, # seconds; long answers need time
max_retries=2, # retries on connection errors, 429 and 5xx
)Create the client once and reuse it; it keeps connections open.
A normal request
r = client.chat.completions.create(
model="claude-sonnet-4-6",
messages=[
{"role": "system", "content": "You are a senior Python reviewer."},
{"role": "user", "content": "Review: def add(a,b): return a+b"},
],
max_tokens=600,
)
print(r.choices[0].message.content)
print(r.usage) # prompt_tokens, completion_tokensStreaming
stream = client.chat.completions.create(model="claude-sonnet-4-6", messages=[{"role": "user", "content": "Tell me a story"}], stream=True)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)Async
import asyncio
from openai import AsyncOpenAI
aclient = AsyncOpenAI(base_url="https://devsaio.lol/v1", api_key=os.environ["DEVSAIO_API_KEY"])
async def ask(q):
r = await aclient.chat.completions.create(model="claude-haiku-5-5", messages=[{"role": "user", "content": q}])
return r.choices[0].message.content
print(asyncio.run(asyncio.gather(*(ask(f"Fact #{i} about Mars") for i in range(5)))))Error handling
import openai
try:
r = client.chat.completions.create(model="claude-sonnet-4-6", messages=[{"role": "user", "content": "hi"}])
except openai.AuthenticationError:
print("Bad or revoked key")
except openai.RateLimitError:
print("Slow down and retry")
except openai.APIStatusError as e:
print("API error", e.status_code, e.message)See handling errors and retries for which errors are safe to retry.
Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.