Skip to main content
Provider methods are deliberately small. The gateway owns provider configuration, stores credentials in its keystore, discovers models, and normalizes model metadata for clients. Provider configuration is workspace-scoped: every provider method takes workspace_id, and API keys are stored under workspace-specific secret ids. A desktop app, CLI, mobile app, or custom client should not talk directly to every model provider just to build a model picker. Use these methods when a client needs to show available providers for a workspace, fetch model catalogs, or update the API key used by that workspace.

​
Methods

MethodParamsResultPurpose
provider/listProviderListParamsProviderListResponseReturn configured provider adapters for a workspace.
provider/models/listProviderListModelsParamsProviderListModelsResponseReturn models known for one provider in a workspace.
provider/set_api_keyProviderSetApiKeyParamsProviderSetApiKeyResponseStore or replace a workspace provider API key.
provider/delete_api_keyProviderDeleteApiKeyParamsProviderDeleteApiKeyResponseRemove a workspace provider API key.

​
Listing Providers

provider/list requires the workspace id because provider configuration belongs to a workspace on the gateway. 
{
  "jsonrpc": "2.0",
  "id": "aaaaaaaaaaaaaaaaaaaaa",
  "method": "provider/list",
  "params": {
    "workspace_id": "ws_000000000000000001"
  }
}
Response: 
{
  "providers": [
    { "name": "openai" },
    { "name": "anthropic" },
    { "name": "openrouter" },
    { "name": "ollama" }
  ]
}
The name is the stable provider identifier used in model_provider, provider/models/list, and API-key methods.

​
Listing Models

Use provider/models/list after the user selects a provider. The gateway returns normalized metadata that a client can use for filtering, badges, warnings, or default selection. 
{
  "jsonrpc": "2.0",
  "id": "bbbbbbbbbbbbbbbbbbbbb",
  "method": "provider/models/list",
  "params": {
    "workspace_id": "ws_000000000000000001",
    "provider": "openai"
  }
}
Response shape: 
{
  "provider": "openai",
  "models": [
    {
      "id": "gpt-5.1",
      "name": "GPT-5.1",
      "description": null,
      "created": null,
      "provider": "openai",
      "owned_by": null,
      "limits": {
        "max_input_tokens": null,
        "max_output_tokens": null,
        "context_window": null
      },
      "capabilities": {
        "vision": true,
        "tool_calling": true,
        "json_output": true,
        "streaming": true,
        "thinking": true,
        "fine_tuning": null,
        "input_modalities": ["text", "image"],
        "output_modalities": ["text"]
      },
      "pricing": null,
      "active": true,
      "family": "gpt",
      "lifecycle_status": null
    }
  ]
}
Model metadata is advisory. Providers differ in how much information they expose, so clients must tolerate null for limits, pricing, lifecycle state, and individual capabilities.

​
Model Metadata

ProviderModelInfo is the normalized model object.
FieldMeaning
idProvider model id. This is the value to put into model.
nameOptional display name.
descriptionOptional model description.
createdOptional provider-created timestamp.
providerProvider id that owns the model entry.
owned_byOptional provider owner string.
limitsOptional input/output/context-window limits.
capabilitiesOptional capability flags and modality lists.
pricingOptional token/image/request pricing metadata.
activeWhether the model should be treated as active.
familyOptional family/group label.
lifecycle_statusOptional provider-specific lifecycle marker.
The important client rule is simple: choose by id, display by name when present, and never require a metadata field that may be null.

​
Setting An API Key

API keys are stored in the gateway keystore under the workspace id and provider name. If the desktop app connects to a remote gateway, the key is stored on that remote gateway, not in the desktop process. 
{
  "jsonrpc": "2.0",
  "id": "ccccccccccccccccccccc",
  "method": "provider/set_api_key",
  "params": {
    "workspace_id": "ws_000000000000000001",
    "provider": "anthropic",
    "api_key": "sk-ant-..."
  }
}
Response: 
{
  "provider": "anthropic",
  "updated": true
}
After updating a key, clients usually refresh provider/models/list for that provider because a newly valid credential can change what the gateway can discover.

​
Deleting An API Key

{
  "jsonrpc": "2.0",
  "id": "ddddddddddddddddddddd",
  "method": "provider/delete_api_key",
  "params": {
    "workspace_id": "ws_000000000000000001",
    "provider": "anthropic"
  }
}
Response: 
{
  "provider": "anthropic",
  "deleted": true
}
Deleting a key does not delete threads or turns that already used that provider. It only affects future provider calls and model discovery in that workspace.

​
Client Behavior

Provider setup is workspace-local inside a gateway. A client connected to three gateways should show provider status for the selected workspace on the selected gateway, because each workspace may have different keys and each gateway may have different local runtime availability and network access. For thread creation and turn execution, pass the selected provider id through model_provider and the selected model id through model. See Threads API and Turns API.