onyx_llm_provider (Resource)

An Onyx LLM provider (OpenAI, Anthropic, Azure, Bedrock, ...) with its enabled models. model_configurations is the full list of record: models omitted from it are removed server-side on apply, and removing the model that is currently the deployment default fails validation — repoint the default first. api_key and custom_config are masked by the API on read, so out-of-band changes to them cannot be detected as drift.

Example Usage

resource "onyx_llm_provider" "openai" {
  name          = "openai-prod"
  provider_type = "openai"
  # api_key is kept in Terraform state. To keep the key out of state, swap in
  # the write-only pair instead (needs Terraform 1.11 or later):
  #   api_key_wo         = var.openai_api_key
  #   api_key_wo_version = 1
  api_key = var.openai_api_key

  # The complete set of enabled models: anything omitted here is
  # removed from the provider on apply.
  model_configurations = [
    { name = "gpt-5" },
    {
      name                = "gpt-5-mini"
      custom_display_name = "GPT-5 Mini (cheap tier)"
    },
    {
      name       = "gpt-5-nano"
      is_visible = false
    },
  ]
}

Schema

Required

• model_configurations (Attributes Set) The complete set of models enabled on this provider. Applies replace the server-side list with exactly this set. (see below for nested schema)
• provider_type (String) LiteLLM provider key, e.g. openai, anthropic, azure, bedrock, vertex_ai, ollama. Must be lowercase.

Optional

NOTE: Write-only arguments are supported in Terraform 1.11 and later.

• api_base (String) Custom API base URL (e.g. for Azure or self-hosted gateways).
• api_key (String, Sensitive) Provider API key. The Onyx API masks this on read, so Terraform cannot detect out-of-band changes; the configured value is authoritative. Prefer api_key_wo, which keeps the value out of state entirely; the two cannot be set together.
• api_key_wo (String, Sensitive, Write-only) Provider API key, held only in configuration. Terraform sends it on every apply and stores nothing, so the key never reaches state. Pair it with api_key_wo_version to rotate it. Needs Terraform 1.11 or later.
• api_key_wo_version (Number) Rotation counter for api_key_wo. Terraform never stores a write-only value and so cannot tell that the secret changed; raise this number to make the next apply send the current one. Do not derive it from the secret itself — unlike the secret, this number is kept in state.
• api_version (String) API version (Azure).
• custom_config (Map of String, Sensitive) Provider-specific config key/values (e.g. Vertex service-account JSON, Bedrock credentials). Masked on read like api_key. Prefer custom_config_wo, which keeps the value out of state entirely; the two cannot be set together.
• custom_config_wo (Map of String, Sensitive, Write-only) Provider-specific config key/values, held only in configuration. Terraform sends them on every apply and stores nothing, so they never reach state. Pair with custom_config_wo_version to rotate them. Needs Terraform 1.11 or later.
• custom_config_wo_version (Number) Rotation counter for custom_config_wo. Terraform never stores a write-only value and so cannot tell that the secret changed; raise this number to make the next apply send the current one. Do not derive it from the secret itself — unlike the secret, this number is kept in state.
• deployment_name (String) Deployment name (Azure).
• force_delete (Boolean) Allow destroying this provider even while it holds the deployment default model. Defaults to false, where such a destroy fails.
• groups (Set of Number) User group ids the provider is restricted to (EE).
• is_auto_mode (Boolean) Onyx Auto mode: the model list is managed by Onyx. When enabled, the server owns model_configurations: Terraform stops drift-checking the list, and updates re-assert the server's current models instead of the configured ones, so registry-managed models are never removed.
• is_public (Boolean) Whether the provider is available to all users.
• name (String) Display name for the provider configuration.
• personas (Set of Number) Persona ids the provider is restricted to.

Read-Only

• id (String) Numeric provider id.

<a id="nestedatt--model_configurations"></a>

Nested Schema for model_configurations

Required:

• name (String) Model name as known to the provider, e.g. gpt-5-mini.

Optional:

• custom_display_name (String) Admin-specified display-name override.
• display_name (String) Source-API display name (dynamic providers such as OpenRouter/Ollama).
• is_visible (Boolean) Whether the model is selectable in the UI.
• max_input_tokens (Number) Override for the model's max input tokens; unset uses the model's known default.
• supports_image_input (Boolean) Override for image-input support; unset lets Onyx infer it.
• supports_reasoning (Boolean) Override for reasoning-model classification; unset lets Onyx infer it.

Import

Import is supported using the following syntax:

The terraform import command can be used, for example:

#!/bin/sh
# Import by numeric provider id. api_key/custom_config are masked by the
# API and stay null until set in configuration.
terraform import onyx_llm_provider.openai 3