> ## Documentation Index > Fetch the complete documentation index at: https://gomodel-feat-vision-routing.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # List all registered models with provider info and access state > GoModel API reference for GET /admin/models: List all registered models with provider info and access state. ## OpenAPI ````yaml /openapi.json get /admin/models openapi: 3.0.0 info: description: >- AI gateway routing requests to multiple LLM providers (OpenAI, Anthropic, Gemini, Groq, Fireworks AI, Meta, OpenRouter, Kilo AI, DeepSeek, Z.ai, xAI, MiniMax, Xiaomi MiMo, OpenCode Go, Oracle, Ollama, Bailian). Drop-in OpenAI-compatible API. title: GoModel API contact: {} version: '1.0' servers: - url: '{base_url}' description: Edit the base URL to point at your GoModel deployment. variables: base_url: default: http://localhost:8080 description: Your GoModel deployment URL security: [] paths: /admin/models: get: tags: - admin summary: List all registered models with provider info and access state parameters: - description: Filter by model category name: category in: query schema: type: string responses: '200': description: OK content: application/json: schema: type: array items: $ref: '#/components/schemas/admin.modelInventoryResponse' maxItems: 10000 description: Bounded by maxItems=10000. '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/core.GatewayError' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/core.GatewayError' security: - BearerAuth: [] components: schemas: admin.modelInventoryResponse: type: object properties: access: $ref: '#/components/schemas/admin.modelAccessResponse' model: $ref: '#/components/schemas/core.Model' provider_name: type: string provider_type: type: string selector: type: string core.GatewayError: type: object properties: code: type: string nullable: true message: type: string param: type: string nullable: true provider: type: string status_code: type: integer type: $ref: '#/components/schemas/core.ErrorType' admin.modelAccessResponse: type: object properties: default_enabled: type: boolean effective_enabled: type: boolean override: $ref: '#/components/schemas/virtualmodels.VirtualModel' selector: type: string user_paths: type: array items: type: string core.Model: type: object properties: created: type: integer id: type: string metadata: description: >- Metadata holds optional enrichment data (display name, pricing, capabilities, etc.). May be nil if the model was not found in the external registry. allOf: - $ref: '#/components/schemas/core.ModelMetadata' object: type: string owned_by: type: string core.ErrorType: type: string enum: - provider_error - rate_limit_error - invalid_request_error - authentication_error - not_found_error - permission_error - internal_error x-enum-varnames: - ErrorTypeProvider - ErrorTypeRateLimit - ErrorTypeInvalidRequest - ErrorTypeAuthentication - ErrorTypeNotFound - ErrorTypePermission - ErrorTypeInternal virtualmodels.VirtualModel: type: object properties: created_at: type: string description: type: string enabled: type: boolean failover: description: >- Failover retries a failed request against the redirect's remaining targets. Tri-state: nil means enabled (the default); explicit false serves the chosen target only. The failover strategy always fails over. type: boolean managed: description: >- Managed marks a virtual model supplied declaratively through config.yaml or the VIRTUAL_MODELS env var rather than the admin store. It is an in-memory flag only: stores never read or write it. Managed rows override store rows of the same Source and are read-only to the admin API. type: boolean model: type: string provider_name: type: string session_affinity: description: >- SessionAffinity keeps requests of one detected session on the target that served it before, while that target stays available. Tri-state: nil means enabled (the default); explicit false restores stateless balancing. type: boolean slowdown: description: >- Slowdown is an extra-time factor from 0.1 to 10; zero disables it. Nil leaves the setting unspecified so an alias can inherit its target model. oneOf: - type: number enum: - 0 - type: number minimum: 0.1 maximum: 10 source: type: string strategy: type: string strategy_config: type: object additionalProperties: {} strategy_plugin: description: >- StrategyPlugin names the routing-strategy plugin consulted when Strategy is "plugin"; StrategyConfig is that plugin's per-virtual-model configuration, validated against its route-scoped fields. Both are cleared for every other strategy. type: string targets: type: array items: $ref: '#/components/schemas/virtualmodels.Target' updated_at: type: string user_paths: type: array items: type: string vision_routing: description: |- VisionRouting sends a request that carries image input only to the targets whose model metadata reports the vision capability. When no target does, every target stays eligible and the provider answers as before. Off by default. type: boolean core.ModelMetadata: type: object properties: capabilities: type: object additionalProperties: type: boolean categories: type: array items: $ref: '#/components/schemas/core.ModelCategory' context_window: type: integer description: type: string display_name: type: string family: type: string max_output_tokens: type: integer modes: type: array items: type: string pricing: $ref: '#/components/schemas/core.ModelPricing' pricing_sources: type: object additionalProperties: type: string rankings: type: object additionalProperties: $ref: '#/components/schemas/core.ModelRanking' tags: type: array items: type: string virtualmodels.Target: type: object properties: model: type: string provider: type: string weight: type: number core.ModelCategory: type: string enum: - all - text_generation - embedding - image - audio - video - utility x-enum-varnames: - CategoryAll - CategoryTextGeneration - CategoryEmbedding - CategoryImage - CategoryAudio - CategoryVideo - CategoryUtility core.ModelPricing: type: object properties: audio_input_per_mtok: type: number audio_output_per_mtok: type: number batch_input_per_mtok: type: number batch_output_per_mtok: type: number cache_write_per_mtok: type: number cached_input_per_mtok: type: number currency: type: string input_per_image: type: number input_per_mtok: type: number output_image_per_mtok: description: >- OutputImagePerMtok prices generated image tokens, which providers bill at a different rate from text output (OpenAI gpt-image-1: $40/Mtok image output and no text output rate at all; Gemini 3 Pro Image: $120/Mtok image output versus $12/Mtok text). It is the output rate on the image endpoints. type: number output_per_mtok: type: number per_character_input: type: number per_image: description: >- PerImage prices a returned image as a flat unit, for models that report no token usage at all (DALL·E, Imagen, grok-imagine). It is an alternative expression of the same charge as OutputImagePerMtok, never an addition to it: catalog entries carry both, so only one may be applied (see usage.CalculateGranularCost). type: number per_page: type: number per_request: type: number per_second_input: type: number per_second_output: type: number reasoning_output_per_mtok: type: number tiers: type: array items: $ref: '#/components/schemas/core.ModelPricingTier' time_windows: description: >- TimeWindows carry rates that replace the base prices during recurring UTC windows (see ModelPricingTimeWindow). Base prices are the standard (peak) rates; use AtTime to resolve the rates in effect at a moment. type: array items: $ref: '#/components/schemas/core.ModelPricingTimeWindow' core.ModelRanking: type: object properties: as_of: type: string elo: type: number rank: type: integer core.ModelPricingTier: type: object properties: cached_input_per_mtok: type: number input_per_mtok: type: number output_per_mtok: type: number up_to_mtok: type: number up_to_tokens: type: integer minimum: 1 core.ModelPricingTimeWindow: type: object properties: label: type: string pricing: $ref: '#/components/schemas/core.ModelPricingTimeWindowRates' utc_ranges: type: array items: $ref: '#/components/schemas/core.ModelPricingUTCRange' core.ModelPricingTimeWindowRates: type: object properties: cache_write_per_mtok: type: number cached_input_per_mtok: type: number input_per_mtok: type: number output_per_mtok: type: number core.ModelPricingUTCRange: type: object properties: days: type: array items: type: string end: type: string start: type: string securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.