Configure Model Providers Enterprise

You configure model providers for your organization's AI features when deploying Dremio. After you configure at least one model provider, you must set a default model provider and can optionally set an allowlist of available models. Dremio uses this default provider for all Dremio's AI agent interactions, whereas the allowlist models can be used by anyone writing AI functions. By default, CALL MODEL is granted to all users for all new model providers, so if the default changes, users can continue to use the AI agent without interruption.

Supported Model Providers

Dremio supports configuration of the following model providers and models. Dremio recommends using enterprise-grade reasoning models for the best performance and experience.

Service	Models	Connection Method(s)
OpenAI	gpt-5 gpt-5-mini gpt-5-nano gpt-4.1 gpt-4o gpt-4-turbo gpt-4.1-mini o3-mini o4-mini o3	Organization ID + API Key
Anthropic	claude-sonnet-4-5 claude-opus-4-1 claude-opus-4 claude-sonnet-4	API Key
Google Gemini	gemini-2.5-pro	API Key
Amazon Bedrock	claude-opus-4-1 claude-opus-4 claude-sonnet-4-5 claude-sonnet-4	Region + Access Key ID + Secret Access Key
Azure OpenAI	claude-opus-4-1 claude-sonnet-4-5 gpt-5 gpt-5-mini gpt-5-nano gpt-4.1 o4-mini o3	Resource Name + Directory ID + Application ID + Client Secret Value
OpenAI-Compatible API	Any model supported by the provider	API endpoint URL, and optionally Organization ID and API Key

note

Dremio does not validate the model associated with an AWS Bedrock model ID or Azure OpenAI deployment name upon model provider creation. Using an unsupported model can lead to runtime errors or a higher rate of inaccurate responses.

Add Model Provider

note

To add a model provider, the AI features preference must be enabled in Preferences.

For steps on adding an AWS Bedrock model provider, see Configure AWS Bedrock as a Model Provider.

For steps on adding an OpenAI-Compatible API model provider, see Configure an OpenAI-Compatible API Model Provider.

For all other model providers, follow these steps to add a model provider in the Dremio console:

1. Click in the side navigation bar to go to the Settings page.
2. Select AI configurations in the settings sidebar.
3. Click Add model provider.

Configure an OpenAI-Compatible API Model Provider

The OpenAI-Compatible API provider lets you connect Dremio to any service that implements the OpenAI API specification, including self-hosted models and third-party providers not listed above, without waiting for Dremio to certify specific models.

To configure an OpenAI-compatible model provider:

1. Click in the side navigation bar to go to the Settings page.
2. Select AI configurations in the settings sidebar.
3. Click Add model provider.
4. In the Add model provider dialog, select OpenAI-Compatible API as the model provider service.
5. For Name, enter a name for the model provider.
6. For API endpoint URL, enter the base URL of your OpenAI-compatible endpoint (for example, https://api.example.com/v1).
7. (Optional) For Organization ID, enter your provider's organization ID.
8. (Optional) For API Key, enter your API key.
9. For Default Model ID, enter the model ID to use as the default.
10. (Optional) For Allowed Model IDs for AI Functions, enter the model IDs to make available for AI functions.
11. (Optional) Expand Advanced Configuration and enter JSON in Model parameters (JSON) to customize model behavior. See Model Parameters.
12. Click Add.

Model Parameters

The Model parameters (JSON) field under Advanced Configuration controls how models behave when called by Dremio. You can set defaults that apply to all models, and override them for specific models by exact name or regex pattern.

Field	Description
parameters	Default parameters applied to all models
per_model	Parameters for a specific model, matched by exact model name
per_model_pattern	Parameters for models whose name matches a regex pattern

Supported Parameters

Parameter	Type	Description
temperature	Number	Controls response randomness. Range: 0.0-1.0. Lower values produce more deterministic output.
max_tokens	Integer	Older parameter name for the maximum number of tokens to generate. Use this for inference servers that do not accept max_completion_tokens.
max_completion_tokens	Integer	Newer parameter name for the maximum number of tokens to generate. Use this for inference servers that do not accept max_tokens.
top_p	Number	Nucleus sampling parameter. Range: 0.0-1.0.
send_user_identifier	Boolean	Whether Dremio sends a user identifier to the provider with each request. Defaults to true. Set to false for providers that do not accept the user field (for example, Mistral).

When the same parameter is defined in multiple places, the most specific definition takes effect: per_model overrides per_model_pattern, which overrides parameters.

Model parameters example

{
  "parameters": {
    "temperature": 0.2,
    "max_tokens": 8192
  },
  "per_model_pattern": {
    ".*mistral.*": {
      "send_user_identifier": false
    }
  },
  "per_model": {
    "gpt-4": {
      "top_p": 0.95,
      "max_tokens": 4096
    }
  }
}

Default Model Provider

To delete the model provider, you must assign a new default unless you are deleting the last available model provider. To update the default model provider to a new one, you must have MODIFY privilege on both the current default and the new proposed default model provider.