cursor0,0
velocity0.00 px/ms
moodcalibrating
api.alloneia.com● 14ms
solar azimuth · awaiting location
v3.2 · live in us-east, eu-west, ap-south
One key.
Every model.
Drop-in replacement for the OpenAI SDK. Point your base_url at alloneia and call GPT, Claude, Gemini, Llama, DeepSeek through one schema, one bill, one auth.
scroll · drag · ↓
Three lines. Every model.
Drop-in replacement for the OpenAI SDK. Change the base_url, keep your code.
$ pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://alloneia.com/api/v1",
api_key="sk-allo-••••••",
)
resp = client.chat.completions.create(
model="claude-haiku-4-5", # or gpt-5, gemini-2.0, llama-3.3...
messages=[{"role": "user", "content": "Hi"}],
)connected · 14 ms
Same upstream price. No markup.
List prices match what each provider charges on their own dashboard. Metered to the token. No minimums. No monthly fees.
Gemini 2.0 Flash
$0.10 / $0.40 · 1M ctx
1.2M req/s
Claude Haiku 4.5
$0.80 / $4.00 · 200K ctx
840k req/s
GPT-4o mini
$0.15 / $0.60 · 128K ctx
2.1M req/s
Llama 3.3 70B
$0.23 / $0.40 · 128K ctx
410k req/s
Mistral Large
$2.00 / $6.00 · 128K ctx
180k req/s
DeepSeek V3
$0.27 / $1.10 · 128K ctx
320k req/s
xAI Grok-2
$2.00 / $10.00 · 131K ctx
95k req/s
See all 47 models
prices · context · benchmarks
Three lines. One bill.
Live in 3 minutes.
01spawn key~ 12 seconds
02paste base_urlno SDK swap
03ship47 models, 1 bill
your key (preview)
sk-allo-v3a8K2nQp7XmL9rT4eY6jB1cF5wH8sN3