> ## 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 organization model > Retrieves a custom model shared with every project in the specified organization, regardless of which project owns it. Returns not found if the model belongs to another organization or is not organization-scoped. ## OpenAPI ````yaml openapi.yaml GET /v2/organizations/{organizationId}/models/{modelId} 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 description: Default environment for APIs security: - bearerAuth: [] paths: /v2/organizations/{organizationId}/models/{modelId}: get: tags: - VolumeService summary: Get organization model description: >- Retrieves a custom model shared with every project in the specified organization, regardless of which project owns it. Returns not found if the model belongs to another organization or is not organization-scoped. operationId: VolumeService_GetOrganizationModel parameters: - name: organizationId in: path required: true schema: type: string description: Organization identifier. - name: modelId in: path required: true schema: description: Model identifier. type: string responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/DE.Model' default: description: Default error response content: application/json: schema: $ref: '#/components/schemas/ErrorData' x-codeSamples: - lang: Python label: Together AI SDK (Python) source: > from together import Together client = Together() identity = client.whoami() if identity.type == "user_jwt": raise RuntimeError("Use a credential scoped to an organization") organization_id = identity.organization.id # The SDK has no dedicated method for this endpoint yet, so call it with # the client's generic GET helper. model = client.get( f"/v2/organizations/{organization_id}/models/ml_abc123", cast_to=object, ) print(model) - lang: TypeScript label: Together AI SDK (TypeScript) source: > import Together from "together-ai"; const client = new Together(); const identity = await client.whoami(); if (identity.type === "user_jwt") { throw new Error("Use a credential scoped to an organization"); } const organizationId = identity.organization.id; const model = await client.models.retrieveOrgModel(organizationId, "ml_abc123"); console.log(model.id, model.name); - lang: JavaScript label: Together AI SDK (JavaScript) source: > import Together from "together-ai"; const client = new Together(); const identity = await client.whoami(); if (identity.type === "user_jwt") { throw new Error("Use a credential scoped to an organization"); } const organizationId = identity.organization.id; const model = await client.models.retrieveOrgModel(organizationId, "ml_abc123"); console.log(model.id, model.name); components: schemas: DE.Model: description: >- Custom or derived model registered in a project and backed by versioned weight files. type: object required: - id - projectId - organizationId - name - weights - visibility properties: id: type: string description: Unique model identifier. projectId: type: string description: ID of the project that owns the model. organizationId: type: string description: ID of the organization that owns the model's project. name: type: string description: >- Project-qualified model name in the form `/`. Create and update requests may use the bare or qualified form. description: type: string description: Human-readable description of the model and its intended use. weights: $ref: '#/components/schemas/DE.ModelWeights' description: >- Architecture, size, precision, and speculative-decoding metadata derived from the model files. baseModelId: type: string description: >- ID of the supported or custom base model from which this model was derived. baseModel: type: string readOnly: true description: >- Resource name of the base model, using `projects/{baseProject}/models/{baseModelId}`; empty when the model has no base. visibility: default: VISIBILITY_PRIVATE enum: - VISIBILITY_PRIVATE - VISIBILITY_INTERNAL type: string description: >- Who can discover the model. `VISIBILITY_PRIVATE` restricts it to the project; `VISIBILITY_INTERNAL` shares it with the organization. createdAt: type: string description: Output only. Timestamp when the model was created. format: date-time readOnly: true updatedAt: type: string description: Output only. Timestamp when the model was last updated. format: date-time readOnly: true 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.ModelWeights: type: object properties: type: enum: - WEIGHTS_TYPE_DEFAULT - WEIGHTS_TYPE_SPECULATOR - WEIGHTS_TYPE_ADAPTER type: string description: >- Role of the weights: full model, speculative draft model, or LoRA adapter. speculatorMechanism: enum: - SPECULATOR_MECHANISM_DRAFT - SPECULATOR_MECHANISM_LOOKAHEAD - SPECULATOR_MECHANISM_MTP type: string description: Speculative decoding mechanism for speculator weights. draftSpeculatorType: enum: - DRAFT_SPECULATOR_TYPE_EAGLE - DRAFT_SPECULATOR_TYPE_PHOENIX type: string description: Draft-model speculator family for draft speculative decoding. architecture: type: string description: Model architecture detected from the weight metadata. contextLength: type: string description: Maximum context length reported by the model metadata. parameters: $ref: '#/components/schemas/DE.ModelParameters' description: Total parameter count and breakdown by numerical data type. description: >- Architecture, size, precision, and speculative-decoding metadata for model weights. DE.ModelParameters: type: object required: - total - byDtype properties: total: type: string description: Total number of parameters in the model weights. byDtype: type: array items: $ref: '#/components/schemas/DE.ModelDTypeCount' description: Parameter counts grouped by numerical data type. description: Model parameter count and precision breakdown. DE.ModelDTypeCount: type: object required: - dtype - count properties: dtype: type: string description: Numerical data type, such as `float16`, `bfloat16`, or `int8`. count: type: string description: Number of model parameters stored with this data type. description: Number of model parameters stored in one numerical data type. securitySchemes: bearerAuth: type: http scheme: bearer x-bearer-format: bearer x-default: default ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.