GPT-4.1
OpenAI · Mid-tier · 128K context
Chat & reasoning model
Rates per million tokens
Input
$2.00
Output
$8.00
Cache read
$0.50
A new account opens on 26.5% off these rates, so input runs at $1.47 per million tokens.
Model id
Pass this as model in any OpenAI-compatible request.
Call it
from openai import OpenAI
client = OpenAI(
base_url="https://api.routedly.ai/v1",
api_key="sk-sr-cli-..."
)
response = client.chat.completions.create(
model="openai-gpt-4-1",
messages=[{"role": "user", "content": "Say hello"}],
)
print(response.choices[0].message.content)Start calling GPT-4.1
One key works across every model in the catalog. No per-provider accounts.