Models

Currently, we offer a single Omnio model through the Chat Completion API.

	omnio-chat-audio-preview
Description	First AI model that can natively reason over audio like humans.
Context window	Up to 45 minutes of input audio with up to 4096 input text tokens, and up to 16,384 output text tokens. Support for longer input audio coming soon.
Max output tokens	16,384 tokens
Pricing	Input: $2.00 per 1M text tokens, $50.00 per 1M audio tokens Output: $10.00 per 1M text tokens
Language	English, support for other languages coming soon.
Training data	Up to January 2024