Anthropic base URL in Python — working examples

Pointing the Anthropic Python SDK at a custom endpoint is one constructor argument. This page shows the four patterns you actually need: sync, streaming, async, and raw HTTP.

In short: Pass base_url to the Anthropic Python client along with your key. The two differences from an OpenAI-shaped integration: auth uses the x-api-key header plus an anthropic-version header, and max_tokens is required on every request.

You need a key before the code below runs. Create an account, generate a key, and copy the base URL (https://aicomp.ai/v1). Create one free →

Check current rates → Free to sign up · $1 minimum top-up · No prepayment

Confirm the key works first. One command, no SDK, costs nothing:

curl https://aicomp.ai/v1/models \
  -H "Authorization: Bearer sk-your-gateway-key"

A JSON list of model IDs means the key is good. Invalid token means it was copied wrong.

Install

pip install anthropic

The basic pattern

from anthropic import Anthropic

client = Anthropic(
    base_url="https://aicomp.ai/v1",          # your endpoint
    api_key="sk-your-gateway-key", # not an Anthropic-issued key
)

resp = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=256,                # required on this API
    messages=[{"role": "user", "content": "Summarise this in one sentence: {text}"}],
)
print(resp.content[0].text)

Two things to note. max_tokens is required — omit it and the request fails validation. And the text lives in content[0].text, not in a choices array.

Streaming

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

Streaming fails loudly if the endpoint does not support SSE, so it is a good compatibility check before you migrate real traffic.

Async

import asyncio
from anthropic import AsyncAnthropic

client = AsyncAnthropic(base_url="https://aicomp.ai/v1", api_key="sk-your-gateway-key")

async def main():
    resp = await client.messages.create(
        model="claude-sonnet-5",
        max_tokens=256,
        messages=[{"role": "user", "content": "say OK"}],
    )
    print(resp.content[0].text)

asyncio.run(main())

Raw HTTP, no SDK

import requests

r = requests.post(
    "https://aicomp.ai/v1/messages",
    headers={
        "x-api-key": "sk-your-gateway-key",
        "anthropic-version": "2023-06-01",
        "content-type": "application/json",
    },
    json={
        "model": "claude-sonnet-5",
        "max_tokens": 256,
        "messages": [{"role": "user", "content": "say OK"}],
    },
    timeout=60,
)
print(r.status_code, r.json())

Note the headers: this API authenticates with x-api-key, not Authorization: Bearer, and it expects an anthropic-version header. Getting these wrong is the most common 401 when moving from an OpenAI-shaped integration.

Reading usage

print(resp.usage.input_tokens, resp.usage.output_tokens)

Log these per request. Output tokens cost several times more than input, so a model that talks more than it needs is measurably more expensive even at the same rate.

Rates for the models above

Claude models reachable from Python — gateway rate vs official list
Model	Gateway rate in / out per 1M tokens	Official list in / out per 1M tokens	Diff
claude-haiku-4-5	$0.5 / $2.5	$1 / $5	50%
claude-sonnet-5	$1 / $5	$2 / $10	50%
claude-opus-5	$2.5 / $12.5	$5 / $25	50%

Rates checked 2026-09-16. Gateway rates move with upstream promotions — verify the current number in your dashboard before committing to a budget.

Troubleshooting

Error	Fix
401 authentication_error	Wrong header. Use `x-api-key`, and include `anthropic-version`.
404 on `/messages`	Doubled `/v1`. Check what your base URL already ends with.
validation error on max_tokens	It is required on this API. Set it.
not_found_error: model	Copy the model ID exactly from the `/models` listing.
Connection reset / SSL error	Usually a proxy. Verify with curl from the same machine.

FAQ

How do I set a custom base URL with the Python Anthropic SDK?

Pass base_url to the Anthropic client constructor along with your api_key. Everything else — the messages call, the parameters, the response parsing — stays the same.

Should the base URL end in /v1?

Include the version segment once. If your endpoint already ends in /v1, do not add it again in the request path, or you will get a 404 from the doubled segment.

Does streaming work with a custom base URL?

Yes, if the endpoint supports SSE. Use the same stream context manager you would against the official API.

Can I use the OpenAI Python SDK with an Anthropic endpoint?

Only if the endpoint exposes an OpenAI-compatible layer for those models. Otherwise use the Anthropic SDK, which is what the examples below do.

Why do I get an SSL or proxy error?

Almost always a corporate proxy or a local firewall rather than the endpoint. Test with curl from the same machine first — if curl works and Python does not, it is your HTTP client configuration.

Get API access