--- title: "Get model" method: GET path: "/v1/models/{model}" tags: ["Models"] --- # Get model `GET /v1/models/{model}` ## Request - Base URL: `https://api.tokenlab.sh` - URL: `https://api.tokenlab.sh/v1/models/{model}` - Auth: HTTP bearer Retrieves current model details, including supported operations, request parameters, request endpoints, selector limits, and pricing when available. Non-chat integrations should read these current model-specific request details before creating a request. ## Path parameters - `model` string, required ## Response `200` Model information - Model - `id` string, required: Model identifier - `object` 'model', required - `created` integer, required: Unix timestamp - `owned_by` string, required: Model provider - `tokenlab` ModelTokenLabExtension, required: TokenLab extension fields for the detail route, including pricing, capabilities, recommendation metadata, and detailed non-chat request metadata. - `aliases` string[] - `deliveryAvailability` object: Current model availability by delivery tier; omitted when the source projection is unavailable. - `verified` boolean, required: Whether this model has eligible TokenLab Verified delivery supply. - `official` boolean, required: Whether this model has eligible Official delivery supply. - `operations` object - `pricing` ScalarPricing: One scalar price layer in USD. Token prices are per 1M tokens. - `input_per_1m` string, nullable, required: Price per 1M input tokens. Null for per-request pricing. - `output_per_1m` string, nullable, required: Price per 1M output tokens. Null for per-request pricing. - `per_request` string, nullable, required: Price per request. Null for per-token pricing. - `is_lock_price` boolean, required: Whether the model is priced per request. - `currency` 'USD', required - `official_pricing` ScalarPricing: One scalar price layer in USD. Token prices are per 1M tokens. - `input_per_1m` string, nullable, required: Price per 1M input tokens. Null for per-request pricing. - `output_per_1m` string, nullable, required: Price per 1M output tokens. Null for per-request pricing. - `per_request` string, nullable, required: Price per request. Null for per-token pricing. - `is_lock_price` boolean, required: Whether the model is priced per request. - `currency` 'USD', required - `capabilities` string[] - `providers` string[] - `max_input_tokens` number, nullable - `max_output_tokens` number, nullable - `category` string - `pricing_unit` string - `cache_pricing` object, nullable: TokenLab Verified prompt-cache prices. Null or omitted when the model has no Verified supply (`deliveryAvailability.verified` is false). - `official_cache_pricing` object, nullable: Official prompt-cache prices. Null or omitted when none are published. - `has_complex_pricing` boolean - `supported_operations` string[] - `pricing_summary` object, nullable - `pricing_provenance` object, nullable - `lifecycle` object, required - `stage` 'active' | 'preview' | 'deprecated' | 'retired', required: Model lifecycle stage for public discovery and display. - `reason` string, nullable, required: Short model lifecycle explanation. - `replacement_model` string, nullable, required: Recommended replacement model when available. - `released_at` string, date-time, nullable, required: Official release date when available. - `deprecated_at` string, date-time, nullable, required: Official deprecation date when available. - `retired_at` string, date-time, nullable, required: Official retirement date when the model is no longer public-discoverable. - `sunset_at` string, date-time, nullable, required: Future sunset date for deprecated models. - `latest` boolean, required: Whether the model should receive a latest badge. - `latest_source` 'auto' | 'override' | 'none', required: How the latest badge was derived. - `latest_window_days` integer, nullable, required: Window used for automatic latest badges. - `commercial` object, required - `user_charge_policy` 'paid' | 'free', required: User billing policy for this model. - `free_reason` 'platform' | 'promotion' | 'null', nullable, required: Reason a model is free to users, if applicable. - `free_until` string, date-time, nullable, required: End time for a temporary free policy, if applicable. - `badges` object[], required: Display badges derived from lifecycle and commercial metadata. - `key` 'free' | 'latest' | 'preview' | 'deprecated' | 'retired', required - `tone` 'green' | 'blue' | 'amber' | 'red' | 'slate', required - `priority` integer, required - `tooltip` object, required - `key` string, required - `values` object, required - `request_format_summary` NonChatRequestFormatSummary, nullable - `public_operations` string[] - `supported_parameters` string[] - `feature_flags` object - `output_formats` string[] - `service_limits` object, nullable - `online_rpm` number, nullable - `concurrency` number, nullable - `offline_inference` boolean - `offline_tpd` string, nullable - `prompt_max_characters` number, nullable - `required_selectors` string[] - `optional_selectors` string[] - `resolutions` string[] - `resolutions_label` string, nullable - `durations` string[] - `durations_label` string, nullable - `aspect_ratios` string[] - `aspect_ratios_label` string, nullable - `request_endpoint` string, nullable - `status_mode` string, nullable - `request_shape_mode` string, nullable - `recommended_request_summary` object, nullable - `request_endpoint_by_operation` object - `operation_constraints` NonChatOperationConstraint[] - `operation` string - `request_endpoint` string, nullable - `request_shape_mode` string, nullable - `status_mode` string, nullable - `supported_parameters` string[] - `required_selectors` string[] - `optional_selectors` string[] - `documented_inputs` string[] - `allowed_resolutions` string[] - `allowed_durations` string[] - `allowed_aspect_ratios` string[] - `notes` string[] - `parameter_options` object - `parameter_value_constraints` object - `request_format_details` NonChatRequestFormatDetails, nullable - `public_operations` string[] - `supported_parameters` string[] - `feature_flags` object - `output_formats` string[] - `service_limits` object, nullable - `online_rpm` number, nullable - `concurrency` number, nullable - `offline_inference` boolean - `offline_tpd` string, nullable - `prompt_max_characters` number, nullable - `required_selectors` string[] - `optional_selectors` string[] - `resolutions` string[] - `resolutions_label` string, nullable - `durations` string[] - `durations_label` string, nullable - `aspect_ratios` string[] - `aspect_ratios_label` string, nullable - `request_endpoint` string, nullable - `status_mode` string, nullable - `request_shape_mode` string, nullable - `recommended_request_summary` object, nullable - `request_endpoint_by_operation` object - `operation_constraints` NonChatOperationConstraint[] - `operation` string - `request_endpoint` string, nullable - `request_shape_mode` string, nullable - `status_mode` string, nullable - `supported_parameters` string[] - `required_selectors` string[] - `optional_selectors` string[] - `documented_inputs` string[] - `allowed_resolutions` string[] - `allowed_durations` string[] - `allowed_aspect_ratios` string[] - `notes` string[] - `parameter_options` object - `parameter_value_constraints` object - `documented_inputs` string[] - `documented_outputs` string[] - `fallback_status_endpoints` string[] - `notes` string[] - `recommended_request` object, nullable - `accepted_request_formats` string[], required: Request formats accepted by this model. ## Other responses - `401`: Unauthorized - Invalid or missing API key - `404`: Model not found - `500`: Internal Server Error --- [API](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway.md) · [All operations](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway/llms.txt) · [OpenAPI document](https://skmtc.dev/tokenlab/apis/tokenlab-ai-gateway/revisions/3208bfbcda22?raw)