> ## Documentation Index > Fetch the complete documentation index at: https://docs.together.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get a supported model > Retrieves a Together-hosted base model and the certified model, configuration, hardware, and performance profiles available for deployment. ## OpenAPI ````yaml GET /supported-models/{id} openapi: 3.1.0 info: title: Together APIs description: The Together REST API. See https://docs.together.ai for more details. version: 2.0.0 termsOfService: https://www.together.ai/terms-of-service contact: name: Together Support url: https://www.together.ai/contact license: name: MIT url: https://github.com/togethercomputer/openapi/blob/main/LICENSE servers: - url: https://api.together.ai/v1 description: Default environment for APIs - url: https://api-inference.together.ai/v2 description: Optimized environment for inference security: - bearerAuth: [] paths: /supported-models/{id}: get: tags: - SupportedModelsService summary: Get a supported model description: >- Retrieves a Together-hosted base model and the certified model, configuration, hardware, and performance profiles available for deployment. operationId: SupportedModelsService_GetSupportedModel parameters: - name: id in: path required: true schema: description: Supported model identifier. type: string responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/DE.SupportedModel' default: description: Default error response content: application/json: schema: $ref: '#/components/schemas/ErrorData' servers: - url: https://api.together.ai/v2 components: schemas: DE.SupportedModel: type: object description: Curated catalog entry for a platform-supported model. required: - id - name - displayName - inputModalities - outputModalities - products - capabilities - publisher - status - displayType - baseModelId - baseModel - deploymentProfiles - createdAt - updatedAt properties: id: type: string description: Unique ID of the deployable Together-hosted base model. name: type: string description: Catalog-controlled HF model ID used for inference. displayName: type: string description: Catalog-controlled human-readable model name. description: type: string description: Human-readable model description. inputModalities: type: array items: enum: - MODALITY_TEXT - MODALITY_IMAGE - MODALITY_AUDIO - MODALITY_VIDEO type: string description: Input modalities supported by the model. outputModalities: type: array items: enum: - MODALITY_TEXT - MODALITY_IMAGE - MODALITY_AUDIO - MODALITY_VIDEO type: string description: Output modalities produced by the model. products: type: array items: enum: - PRODUCT_SERVERLESS - PRODUCT_DEDICATED - PRODUCT_FINE_TUNING type: string description: Product surfaces where the model is offered. features: type: array items: enum: - FEATURE_TOOL_CALLING - FEATURE_STRUCTURED_OUTPUT - FEATURE_REASONING type: string description: Advanced features exposed by the model. capabilities: type: array items: enum: - CAPABILITY_CHAT - CAPABILITY_EMBEDDING - CAPABILITY_RERANKING - CAPABILITY_IMAGE_GENERATION - CAPABILITY_VIDEO_GENERATION type: string description: High-level tasks the model supports. architecture: type: string description: Model architecture from the underlying weights metadata. contextLength: type: string description: Maximum context length from the underlying weights metadata. publisher: type: string description: Organization or publisher associated with the model. status: enum: - SUPPORTED_MODEL_STATUS_RECOMMENDED - SUPPORTED_MODEL_STATUS_SUPPORTED - SUPPORTED_MODEL_STATUS_DEPRECATED - SUPPORTED_MODEL_STATUS_HIDDEN type: string description: Catalog recommendation status for the model. tags: type: array items: type: string description: Searchable catalog tags for the model. inputFormat: type: string description: Preferred input format for the model. outputFormat: type: string description: Preferred output format for the model. serverlessEndpoint: type: string description: Serverless endpoint name for inference, if available. familyId: type: string description: Model family identifier for related catalog entries. displayType: type: string description: >- UI-facing model type badge, such as chat, language, code, image, embedding, rerank, moderation, audio, video, or transcribe. baseModelId: type: string description: >- Bare model ID for the architecture's base model; empty when no base model is linked. baseModel: type: string description: >- Resource name for the base model as `projects/{projectId}/models/{modelId}`; empty when unresolved. deploymentProfiles: type: array items: $ref: '#/components/schemas/DE.SupportedModelDeploymentProfile' description: Certified deployment profiles available for the model. createdAt: type: string format: date-time description: Timestamp when the catalog entry was created. updatedAt: type: string format: date-time description: Timestamp when the catalog entry was last updated. ErrorData: type: object required: - error properties: error: type: object properties: message: type: string nullable: false type: type: string nullable: false param: type: string nullable: true default: null code: type: string nullable: true default: null required: - type - message DE.SupportedModelDeploymentProfile: type: object description: Certified deployment profile for a supported model. required: - profileId - certifiedConfigRevisionId - certifiedModelRevisionId - gpuType - gpuCount - quantization - performanceBenchmarks - config - model - parallelism properties: profileId: type: string description: Stable profile identifier, usually the certified config id. certifiedConfigRevisionId: type: string description: Certified configuration revision identifier. certifiedModelRevisionId: type: string description: Certified model weight revision identifier, if available. gpuType: type: string description: GPU instance type for the profile. gpuCount: type: integer description: Number of GPUs required by the profile. quantization: type: string description: Quantization method for the profile, if available. tensorParallelSize: type: integer description: >- Deprecated. Use `parallelism`. Legacy tensor-parallel shard count for the profile. deprecated: true performanceBenchmarks: $ref: '#/components/schemas/DE.SupportedModelPerformanceBenchmarks' description: Performance benchmarks for the profile, if available. config: type: string description: >- Certified config revision in the form `projects/{projectId}/configs/{configRevisionId}`. Omitted when the profile does not pin a config. model: type: string description: >- Deployable model resource in the form `projects/{projectId}/models/{modelId}[/revisions/{revisionId}]`. Omitted when the profile does not pin model weights. parallelism: type: string description: >- Free-form parallelism spec for the profile, such as TP8, TP4, EP, or PD; supersedes tensor_parallel_size. DE.SupportedModelPerformanceBenchmarks: type: object description: Performance benchmark metrics for a supported model profile. properties: decodingSpeedTps: type: number format: double description: Decoding throughput in tokens per second. timeToFirstTokenMs: type: integer description: Time to first token in milliseconds. maxContextLength: type: string description: Maximum context length supported by the profile. securitySchemes: bearerAuth: type: http scheme: bearer x-bearer-format: bearer x-default: default ````