LLM Configurations

Configure LLM provider API keys for your platform. Each provider key is encrypted with AES-256-GCM before storage and decrypted at runtime by the inference service.

How Provider Routing Works

When an end user requests a model (e.g. gpt-4o), the inference service:

Looks up all enabled model_provider_configs for that model slug
Finds your platform's active provider key for the matching provider
Decrypts the API key
Routes the request to the provider

Providers and models are managed by the system admin via /v1/admin/providers and /v1/admin/models. Platform owners only need to add their own provider API keys.

GET/v1/platforms/{platformId}/llm-configs

Lists provider key configurations for the platform. API keys are never returned.

Auth: Platform key.

bash

curl https://api.assistiv.ai/v1/platforms/{platformId}/llm-configs \
  -H "Authorization: Bearer sk-plat_your_key"

json

{
  "data": [
    {
      "id": "uuid",
      "platform_id": "uuid",
      "provider_id": "uuid",
      "is_default": true,
      "is_active": true,
      "created_at": "2025-01-15T10:30:00Z"}
  ],
  "total": 1, "page": 1, "limit": 20
}

POST/v1/platforms/{platformId}/llm-configs

Adds a provider API key. The key is encrypted before storage.

Auth: Platform key.

Request Body

Name	Type	Required	Description
provider_id	string	Required	UUID of the provider (OpenAI, Anthropic, etc.).
api_key	string	Required	Your provider API key. Encrypted with AES-256-GCM before storage.
is_default	boolean	Optional	Set as the default key for this provider on your platform.Default: `false`

⚠Security

Provider API keys are encrypted at rest and never returned in API responses. Only the metadata (provider, default status, active status) is visible.

bash

curl -X POST https://api.assistiv.ai/v1/platforms/{platformId}/llm-configs \
  -H "Authorization: Bearer sk-plat_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "provider_id": "provider-uuid-for-openai",
    "api_key": "sk-openai-your-key-here",
    "is_default": true
  }'

PATCH/v1/platforms/{platformId}/llm-configs/{configId}

Updates a provider key configuration. Triggers cache invalidation.

Auth: Platform key.

Request Body

Name	Type	Required	Description
api_key	string	Optional	New provider API key (will be re-encrypted).
is_default	boolean	Optional	Update default status.
is_active	boolean	Optional	Enable or disable this key.

bash

curl -X PATCH https://api.assistiv.ai/v1/platforms/{platformId}/llm-configs/{configId} \
  -H "Authorization: Bearer sk-plat_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "api_key": "sk-openai-new-key",
    "is_default": true,
    "is_active": true
  }'

DELETE/v1/platforms/{platformId}/llm-configs/{configId}

Deletes a provider key configuration. Triggers cache invalidation.

Auth: Platform key. Returns 204 No Content.

bash

curl -X DELETE https://api.assistiv.ai/v1/platforms/{platformId}/llm-configs/{configId} \
  -H "Authorization: Bearer sk-plat_your_key"