Nitro Variant

High-speed model inference with :nitro

The :nitro variant provides high-speed inference for faster response times.

Usage

Append :nitro to any model ID:

1 {
2   "model": "openai/gpt-4o:nitro"
3 }

Nitro variants prioritize speed and low latency, making them ideal for real-time applications where fast response times are critical.