> ## Documentation Index > Fetch the complete documentation index at: https://ngrok.com/docs/llms.txt > Use this file to discover all available pages before exploring further. > List every model available to your account, including built-in catalog models and your own user-defined provider models. # List available AI Gateway models ## OpenAPI ````yaml openapi/ai-gateway.yaml GET /v1/models openapi: 3.0.3 info: title: AI Gateway APIs version: 0.1.0 description: | Control-plane HTTP APIs served by the ai-gateway-control service. servers: - url: https://api.ngrok.ai security: - bearerAuth: [] tags: - name: AI Gateway Access Key Configurations description: Manage reusable access key configurations (scope and routing rules). - name: AI Gateway Access Keys description: Manage ngrok-managed access keys associated with AI Gateway endpoints. - name: AI Gateway Configuration description: >- Manage per-account AI Gateway configuration (timeouts, token caps, metadata). - name: AI Gateway API Keys description: Manage customer-facing AI Gateway API Keys. - name: AI Gateway Credits description: >- Purchase AI Gateway credits, via Stripe Checkout or a charge of the saved card, and read purchase/transaction history. - name: AI Gateway Providers description: Manage AI Gateway providers and the models they expose. - name: AI Gateway Custom Providers description: Manage custom AI Gateway providers and the models they expose. - name: AI Gateway Models description: >- Read-only listing of AI Gateway models available to the authenticated account. - name: AI Gateway Provider Keys description: Manage provider keys attached to AI Gateway managed access keys. - name: AI Gateway Usage description: >- Read-only AI Gateway usage events and aggregated usage overview for the authenticated account. paths: /v1/models: get: tags: - AI Gateway Models summary: List available AI Gateway models description: > List every model available to the authenticated account through the AI Gateway — both built-in ngrok catalog models and the account's own user-defined provider models. Shaped to align with the OpenAI/Anthropic `/v1/models` convention so existing SDKs and tooling can consume it directly. operationId: ListAIGatewayModels responses: '200': description: The available AI Gateway models. content: application/json: schema: $ref: '#/components/schemas/AIGatewayModelList' default: $ref: '#/components/responses/Error' components: schemas: AIGatewayModelList: type: object additionalProperties: false required: - object - data properties: object: type: string enum: - list description: Object type; always "list". data: type: array description: The available AI Gateway models. items: $ref: '#/components/schemas/AIGatewayModel' AIGatewayModel: type: object additionalProperties: false required: - id - name - created - architecture - slug - object - owned_by - providers properties: id: type: string description: Model ID. name: type: string created: type: integer format: int64 description: Inventory creation time as Unix seconds. released: type: integer format: int64 description: Model release time as Unix seconds, when known. description: type: string architecture: type: object additionalProperties: false required: - modality - input_modalities - output_modalities properties: modality: type: string input_modalities: type: array items: type: string output_modalities: type: array items: type: string tokenizer: type: string instruction_type: type: string slug: type: string description: Short model ID. object: type: string enum: - model description: Object type; always "model". owned_by: type: string enum: - organization_owned - ngrok description: > Catalog owner: "ngrok" for built-in catalog models, "organization_owned" for the account's own user-defined provider models. providers: type: array description: Providers offering this model. items: $ref: '#/components/schemas/AIGatewayModelProvider' Error: type: object additionalProperties: false required: - statusCode - msg - details properties: errorCode: type: string description: Stable ngrok error code when available. statusCode: type: integer format: int32 description: HTTP status code for this error. msg: type: string description: Human-readable error message. details: type: object description: Structured error details. additionalProperties: type: string AIGatewayModelProvider: type: object additionalProperties: false required: - model_id - id - display_name - context_length - status - pricing - supported_api_formats - supports_implicit_caching properties: model_id: type: string description: Provider-qualified model ID. id: type: string description: Provider ID. display_name: type: string description: Provider name. logo_url: type: string website_url: type: string context_length: type: integer description: Maximum context window in tokens; zero when unknown. max_input_tokens: type: integer max_completion_tokens: type: integer description: Maximum output tokens the model supports, when known. supports_implicit_caching: type: boolean description: >- Whether this provider caches repeated prompts automatically for this model. status: type: string enum: - active - inactive pricing: $ref: '#/components/schemas/AIGatewayModelPricing' supported_api_formats: type: array description: API formats supported by the provider for this model. items: $ref: '#/components/schemas/AIGatewayModelSupportedAPIFormat' metrics: $ref: '#/components/schemas/AIGatewayModelProviderMetrics' AIGatewayModelPricing: type: object additionalProperties: false required: - currency - rates properties: currency: type: string description: Pricing currency; currently "USD". rates: type: array description: Provider pricing rates. items: $ref: '#/components/schemas/AIGatewayModelPricingRate' AIGatewayModelSupportedAPIFormat: type: object additionalProperties: false required: - format - name - path - parameters properties: format: type: string description: API format identifier, such as "openai" or "anthropic". name: type: string description: API surface name. enum: - chat-completions - responses - messages - generate-content path: type: string description: | HTTP path for this API surface. The `generate-content` surface names its model in the path, so that path holds this model's id. Its streaming form replaces the `:generateContent` verb with `:streamGenerateContent`. parameters: type: array description: Parameters supported for this API surface and model. items: type: string AIGatewayModelProviderMetrics: type: object additionalProperties: false properties: uptime_last_15m: type: number format: double description: >- Percentage of eligible provider attempts that returned 2xx during the last 15 minutes. Omitted when the window has no eligible attempts. uptime_last_1h: type: number format: double description: >- Percentage of eligible provider attempts that returned 2xx during the last 60 minutes. Omitted when the window has no eligible attempts. uptime_last_1d: type: number format: double description: >- Percentage of eligible provider attempts that returned 2xx during the last 24 hours. Omitted when the window has no eligible attempts. throughput_last_1h: allOf: - $ref: '#/components/schemas/AIGatewayModelQuantiles' description: Output tokens per second during the last hour. latency_last_1h: allOf: - $ref: '#/components/schemas/AIGatewayModelQuantiles' description: Time to first token in milliseconds during the last hour. AIGatewayModelPricingRate: type: object additionalProperties: false required: - type - unit - price properties: type: type: string description: >- Billing type, such as "prompt", "completion", or "input_cache_write". unit: type: string description: Billing unit, such as "token", "request", "image", or "second". price: type: string description: Cost per billing unit. conditions: $ref: '#/components/schemas/AIGatewayModelPricingRateConditions' AIGatewayModelQuantiles: type: object additionalProperties: false required: - p50 - p95 properties: p50: type: number format: double description: 50th percentile. p95: type: number format: double description: 95th percentile. window_minutes: type: integer format: int32 description: >- Length of the window that produced these quantiles, in minutes. A wider window is used when the last hour holds too few samples. as_of: type: string format: date-time description: >- When these quantiles were measured. Present only when the value comes from an earlier window because no recent window holds enough samples. AIGatewayModelPricingRateConditions: type: object additionalProperties: false properties: ttl: type: string description: Cache lifetime, such as "5m" or "1h". min_input_tokens: type: integer description: Minimum input-token count for this rate. max_input_tokens: type: integer description: Maximum input-token count for this rate. quality: type: string description: Image, audio, or video quality tier. resolution: type: string description: Resolution associated with this rate. service_tier: type: string description: Provider service tier associated with this rate. responses: Error: description: API error response. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer ````