Skip to main content
Omni AI is in early access. Reach out to your account manager or Omni support to have it enabled for your organization.
Omni AI lets your organization use AI in Omni at no cost. Requests that run on Omni AI don’t use AI credits, so your users can ask questions and get answers without spending your credits.

​
How it works

Omni chooses the model behind Omni AI and the provider that runs it. Omni doesn’t host the model. Instead, Omni AI runs on one of Omni’s approved inference providers. Omni AI is opt-in and off by default. To start using it:
  1. Ask Omni to enable Omni AI for your organization by contacting either your account manager or Omni support.
  2. A user with Organization Admin permissions turns on Omni AI. See LLM settings for more information.

​
Inference providers and models

Omni AI runs on one of the following approved inference providers:
  • Baseten
  • Amazon Bedrock
  • Microsoft Foundry (Azure)
And uses one of the following models:
  • DeepSeek V4.1 Flash 1017
  • GLM 5.3 Flash
Omni may switch the provider or the model at any time. For the regions where each provider processes AI requests, see AI inference regions.

​
Next steps