Three steps. Five dollars. Every model.
Create an account and add $5 to your balance. No subscriptions, no commitments.
Generate an API key from your dashboard. It works everywhere OpenAI's key works.
Point any OpenAI-compatible client at our endpoint. GPT-4, Claude, Gemini — one key.
OpenAI, Anthropic, Google, and more. Route to any model through a single unified API.
Full SSE streaming support. Token-by-token delivery, exactly like the native APIs.
Drop-in replacement. Change one line — your base URL — and every tool just works.
Pay per token, see costs live. No surprises. Every cent tracked and visible on stream.
If you can use OpenAI, you can use Leone.
from openai import OpenAI client = OpenAI( base_url="https://hjleone.com/v1", api_key="hjl-your-api-key", ) response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello, Leone."}], stream=True, ) for chunk in response: print(chunk.choices[0].delta.content, end="")
Cost-plus pricing. You see what the providers charge; we add a thin margin.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| gpt-4o | $2.75 | $11.00 |
| gpt-4o-mini | $0.165 | $0.66 |
| gpt-4-turbo | $11.00 | $33.00 |
| claude-sonnet-4-20250514 | $3.30 | $16.50 |
| claude-3-5-haiku | $0.88 | $4.40 |
| claude-3-opus | $16.50 | $82.50 |
| gemini-1.5-pro | $1.38 | $5.50 |
| gemini-1.5-flash | $0.083 | $0.33 |
| llama-3.1-70b | $0.77 | $0.83 |
$5 gets you started. No subscriptions. Pay only for what you use.
Create Account