Providers

Posit Assistant works with a range of model providers, though the exact set and how you set them up varies by platform. This page covers the providers available on RStudio and the Terminal (TUI).

If you are using Posit Assistant in Positron, please see Positron’s provider documentation, which covers the account, authentication, and settings for each provider. Providers are configured through Positron’s built-in provider dialog rather than the settings described below.

Supported Providers

The following providers are available on RStudio and the Terminal (TUI):

Provider	Authentication
Posit AI	Sign in (OAuth)
Anthropic	API key
OpenAI	API key
Google Gemini	API key
OpenRouter	API key
DeepSeek	API key
Amazon Bedrock	AWS credentials
Google Vertex AI (Experimental)	Google Cloud credentials
Microsoft Foundry	API key
Snowflake Cortex	`connections.toml` or API key
Databricks (Experimental)	Workspace URL + token or OAuth
OpenAI Compatible	Base URL (API key optional)

Configuring Providers

How you configure providers depends on your platform:

RStudio — Providers can be configured through the assistant settings UI.
Terminal (TUI) — Press Ctrl+O to open the provider configuration screen, where you can sign in or enter credentials for supported providers. Providers that require additional connection settings may need environment variables or the config file; see their setup notes below.

For most API-key providers (Anthropic, OpenAI, Gemini, DeepSeek, OpenRouter, etc.), you just need an API key from the provider’s website. The sections below cover providers that need additional setup.

Provider Setup

Posit AI

Posit AI is a managed service from Posit that gives you access to frontier LLMs through a single account. It’s the easiest way to get started — sign in once with no API keys to manage. See the Posit AI documentation for account setup, available models, and billing.

Amazon Bedrock

Amazon Bedrock uses AWS credentials rather than an API key. Configure access using the AWS CLI:

Install the AWS CLI and run aws configure to set up your credentials.
Ensure your IAM user or role has permissions to invoke Bedrock models (bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream) and to discover them (bedrock:ListFoundationModels and bedrock:ListInferenceProfiles). Without bedrock:ListInferenceProfiles, model listing still works in us-, eu-, and ap- regions via a legacy fallback, but other regions (such as ca-central-1 or me-central-1) require it and will show no models.

You can specify a region and profile via the config file or environment variables (AWS_REGION, AWS_PROFILE).

Bedrock support is experimental in both AWS GovCloud regions: us-gov-west-1 and us-gov-east-1. Standard endpoints are used by default. To require AWS FIPS endpoints, set AWS_USE_FIPS_ENDPOINT=true, or set use_fips_endpoint = true in the selected AWS profile in your shared AWS config file. The environment variable takes precedence over the profile setting, including an explicit value of false. use_fips_endpoint is an AWS shared-config setting, not a providers.json field.

Google Vertex AI

Google Vertex AI uses Google Cloud Application Default Credentials. Install the Google Cloud CLI, then authenticate:

gcloud auth application-default login

Configure your project and location in the config file:

{
  "providers": {
    "google-vertex": {
      "googleCloud": {
        "project": "my-gcp-project",
        "location": "us-central1"
      }
    }
  }
}

Snowflake Cortex

Posit Assistant can authenticate to Snowflake Cortex two ways:

From a connections.toml connection (recommended). If you already have a Snowflake connections.toml (used by the Snowflake CLI and Python connector), the configuration screen discovers its connections and lets you pick one. The credential is then acquired automatically based on the connection’s authenticator — external-browser single sign-on (EXTERNALBROWSER), key-pair JWT (SNOWFLAKE_JWT), a programmatic access token, or OAuth. The account host is derived from the connection’s account/host/region, so no base URL is needed.
With a token and base URL. Alternatively, enter a token directly along with a base URL pointing to your account’s Cortex endpoint.

connections.toml is discovered from the standard locations ($SNOWFLAKE_HOME, ~/.snowflake, or the per-platform default directory); you can also point at a specific directory with the providers.snowflake-cortex.snowflake.home setting in the config file.

OpenAI Compatible

Connect to any endpoint that implements the OpenAI chat completions API. A base URL is required; an API key is optional (for unauthenticated local servers).

This is useful for self-hosted models, alternative API providers, or any service that exposes an OpenAI-compatible interface.

Ollama

Ollama runs models locally on your machine. Install Ollama, pull a model, and you’re ready to go:

ollama pull llama3.2

No API key or credentials are needed. If Ollama is running on a non-default endpoint, configure it via the OLLAMA_ENDPOINT environment variable or the providers.ollama.endpoint setting in the config file.

LM Studio

LM Studio provides a local model server with a graphical interface. Install LM Studio, download a model, and start the local server. No API key or credentials are needed.

Databricks

📝 Experimental

Databricks support is experimental. Not all features may work correctly.

Posit Assistant can discover and use models served by a Databricks workspace (Model Serving foundation models, external models, and custom serving endpoints). Every authentication method requires the workspace URL, such as https://dbc-example.cloud.databricks.com.

On RStudio and the Terminal (TUI), authenticate with a personal access token or service-principal OAuth. See the Databricks reference for setup, environment variables, and model availability details.

Custom Base URLs and Headers

Provider base URLs and custom HTTP headers can be configured in the config file under the providers key. This is useful for enterprise proxies or custom API gateways. Some providers require a version segment in the base URL — see the config file reference for the baseUrl, customHeaders, and endpoint settings and the exact URL formats each provider expects.

Environment Variables

Provider credentials can also be set via environment variables. Environment variables take precedence over file-based configuration.

Environment variables must be set before the host environment (RStudio) starts, so for day-to-day IDE use the settings UI or config file is usually more practical. Environment variables are most useful for the TUI, CI/CD pipelines, and containerized deployments.

Variable	Description
`ANTHROPIC_API_KEY`	API key for the Anthropic provider
`ANTHROPIC_BASE_URL`	Custom base URL for the Anthropic provider
`OPENAI_API_KEY`	API key for the OpenAI provider
`OPENAI_BASE_URL`	Custom base URL for the OpenAI provider
`GEMINI_API_KEY`	API key for the Gemini provider
`GEMINI_BASE_URL`	Custom base URL for the Gemini provider
`OPENAI_COMPATIBLE_API_KEY`	API key for the OpenAI Compatible provider
`OPENAI_COMPATIBLE_BASE_URL`	Custom base URL for the OpenAI Compatible provider

⚠️ API keys

Never commit API keys to version control. Use environment variables or a secrets manager for sensitive credentials.