Python SDK

Two Python paths — anthropic for native Claude code, openai for migrations. Both work with one base_url change.

Install

pip3 install anthropic
# or, for OpenAI-style code:
pip3 install openai
# In a venv (recommended):
# python3 -m venv .venv && source .venv/bin/activate
# pip install anthropic openai

Anthropic SDK

import os
from anthropic import Anthropic
client = Anthropic(
api_key=os.environ["ONEPROVIDER_KEY"],
base_url="https://api.oneprovider.dev",
)
resp = client.messages.create(
model="claude-sonnet-5-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Say hi."}],
)
print(resp.content[0].text)

OpenAI-compatible

import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ONEPROVIDER_KEY"],
base_url="https://api.oneprovider.dev/v1",
)
resp = client.chat.completions.create(
model="claude-sonnet-5-5",
messages=[{"role": "user", "content": "Say hi."}],
)
print(resp.choices[0].message.content)

Async client

import asyncio
from anthropic import AsyncAnthropic
async def main():
client = AsyncAnthropic(base_url="https://api.oneprovider.dev")
resp = await client.messages.create(
model="claude-sonnet-5-5",
max_tokens=512,
messages=[{"role": "user", "content": "Hi async."}],
)
print(resp.content[0].text)
asyncio.run(main())

Streaming

with client.messages.stream(
model="claude-sonnet-5-5",
max_tokens=512,
messages=[{"role": "user", "content": "Tell me a haiku."}],
) as stream:
for chunk in stream.text_stream:
print(chunk, end="", flush=True)

Tool use

tools = [{
"name": "get_weather",
"description": "Get current weather for a city.",
"input_schema": {
"type": "object",
"properties": {"city": {"type": "string"}},
"required": ["city"],
},
}]
resp = client.messages.create(
model="claude-sonnet-5-5",
max_tokens=1024,
tools=tools,
messages=[{"role": "user", "content": "What's the weather in Frankfurt?"}],
)
# resp.stop_reason == "tool_use"
# Inspect resp.content for tool_use blocks.

Retry & error handling

from anthropic import APIStatusError
from tenacity import retry, stop_after_attempt, wait_exponential
@retry(
stop=stop_after_attempt(3),
wait=wait_exponential(multiplier=0.5, min=0.5, max=4),
retry_error_cls=APIStatusError,
)
def call():
return client.messages.create(
model="claude-sonnet-5-5",
max_tokens=512,
messages=[{"role": "user", "content": "Hi."}],
)

Which model to choose

Pass the id in model. claude-sonnet-5-5 is the default for most code, claude-haiku-5-5 for fast, high-volume calls and claude-opus-5-5 for hard reasoning. The OpenAI-compatible form also accepts GPT ids such as gpt-5.6-terra. Use the Anthropic form with https://api.oneprovider.dev and the OpenAI form with https://api.oneprovider.dev/v1. Ids are on the models page .

Common errors and fixes

404 NotFoundError

Anthropic SDK: base_url="https://api.oneprovider.dev" with no /v1. OpenAI SDK: base_url="https://api.oneprovider.dev/v1" with /v1.

401 AuthenticationError

The environment variable is empty or has a trailing newline. Print len(os.environ["ONEPROVIDER_KEY"]) before the call.

429 RateLimitError

Check the message: “Insufficient balance” means top up (do not retry), any other 429 is a rate limit, so back off and respect Retry-After.

APIConnectionError or read timeout

Disable VPN or proxy variables (HTTPS_PROXY), and use streaming for long answers: a non-streaming request must start within 6 minutes.

400 about max_tokens

The Anthropic SDK requires max_tokens in every request.

FAQ

Can I keep the official SDKs?

Yes. Only the key and base_url change, see migrate from Anthropic and migrate from OpenAI .

Does streaming work?

Yes, with both SDKs; see Streaming .

Where do I keep the key?

In an environment variable, never in the repository.

Quick answers

Which base URL do I use?

Claude Code and Anthropic SDKs use https://api.oneprovider.dev. OpenAI SDKs and OpenAI-compatible clients use https://api.oneprovider.dev/v1. One key works behind both; the model list is on the models page ; rates are on the pricing page .

How do I authenticate?

Send the raw sk-… key in x-api-key or Authorization: Bearer: one of them, never both. Keep the key in an environment variable, not in a file that gets committed. More on authentication .

Where do I get a key?

Open your cabinet in the Telegram bot @oneprovider_robot or at app.oneprovider.dev, top up the balance and press “Issue a key”. Each key can carry its own spend limit. Cabinet & API keys .

What do 401, 404 and 429 mean?

401: the key is missing, mistyped or sent in the wrong header; paste the whole key without quotes or spaces. 404: usually a wrong base URL, for example a missing or doubled /v1. 429 with “Insufficient balance”: the cabinet balance or the key’s spend limit is used up, so top up instead of retrying; any other 429 is a rate limit, so wait for Retry-After. Details: error codes and troubleshooting .

Why do streams cut off or reset?

VPN and VLESS proxies often buffer SSE or break HTTP/2 negotiation. OneProvider has no regional restrictions and does not buffer streams, so turn the proxy off and retry.

Where do I ask if this is not enough?

Message @Oneproviderhelpbot on Telegram or open “Support” in the web cabinet, with the HTTP status code and the exact error message. How support works .