> ## Documentation Index > Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Model > ### Description Creates and hosts a model based on a model template. Base embedding models, chunk ranking functions, and LLMs are often not sufficient for customer use cases. We have shown in various blogs that fine-tuning these models on customer data can lead to significant improvements in performance. 1. [We Fine-Tuned GPT-4 to Beat the Industry Standard for Text2SQL]( https://scale.com/blog/text2sql-fine-tuning) 2. [OpenAI Names Scale as Preferred Partner to Fine-Tune GPT-3.5]( https://scale.com/blog/open-ai-scale-partnership-gpt-3-5-fine-tuning) 3. [How to Fine-Tune GPT-3.5 Turbo With OpenAI API]( https://scale.com/blog/fine-tune-gpt-3.5) ### Details Before creating a model, you must first create a model template. A model template serves 2 purposes. First, it provides common scaffolding that is static across multiple models. Second, it exposes several variables that can be injected at model creation time to customize the model. For example, a model template can define a docker image that contains code to run a HuggingFace or SentenceTransformers model. This docker image code also accepts environment variables that can be set to swap out the model weights or model name. Refer to the Create Model Template API for more details. To create a new model, users must refer to an existing model template and provide the necessary parameters the the model template requires in its `model_creation_parameters_schema` field. The combination of the model template and the model creation parameters will be used to create and deploy a new model. Once a model has been created, it can be executed by calling the Execute Model API. ### Coming Soon Some of our EGP APIs depend on models, for example Knowledge Base APIs depend on embedding models, Chunk Ranking APIs depend on ranking models, and Completion APIs depend on LLMs. In the near future, if a model is created from a model template that is compatible with one of these APIs (based on the model template's `model_type field`), the model will automatically be registered with the API. This will allow users to immediately start using the model with those API without any additional setup. ## OpenAPI ````yaml https://app.stainlessapi.com/api/spec/documented/sgp/openapi.yml post /v4/models openapi: 3.1.0 info: title: EGP API V4 description: >- This is the parent API for all EGP APIs. If you are looking for the EGP API, please go to https://api.egp.scale.com/docs. contact: name: Scale Generative AI Platform url: https://scale.com/genai-platform version: 0.1.0 servers: - url: https://api.egp.scale.com security: [] tags: - name: Models description: Model API. paths: /v4/models: post: tags: - Models summary: Create Model description: >- ### Description Creates and hosts a model based on a model template. Base embedding models, chunk ranking functions, and LLMs are often not sufficient for customer use cases. We have shown in various blogs that fine-tuning these models on customer data can lead to significant improvements in performance. 1. [We Fine-Tuned GPT-4 to Beat the Industry Standard for Text2SQL]( https://scale.com/blog/text2sql-fine-tuning) 2. [OpenAI Names Scale as Preferred Partner to Fine-Tune GPT-3.5]( https://scale.com/blog/open-ai-scale-partnership-gpt-3-5-fine-tuning) 3. [How to Fine-Tune GPT-3.5 Turbo With OpenAI API]( https://scale.com/blog/fine-tune-gpt-3.5) ### Details Before creating a model, you must first create a model template. A model template serves 2 purposes. First, it provides common scaffolding that is static across multiple models. Second, it exposes several variables that can be injected at model creation time to customize the model. For example, a model template can define a docker image that contains code to run a HuggingFace or SentenceTransformers model. This docker image code also accepts environment variables that can be set to swap out the model weights or model name. Refer to the Create Model Template API for more details. To create a new model, users must refer to an existing model template and provide the necessary parameters the the model template requires in its `model_creation_parameters_schema` field. The combination of the model template and the model creation parameters will be used to create and deploy a new model. Once a model has been created, it can be executed by calling the Execute Model API. ### Coming Soon Some of our EGP APIs depend on models, for example Knowledge Base APIs depend on embedding models, Chunk Ranking APIs depend on ranking models, and Completion APIs depend on LLMs. In the near future, if a model is created from a model template that is compatible with one of these APIs (based on the model template's `model_type field`), the model will automatically be registered with the API. This will allow users to immediately start using the model with those API without any additional setup. operationId: POST-V4-/models requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ModelInstanceRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ModelInstanceResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: Python source: |- import os from scale_gp import SGPClient client = SGPClient( api_key=os.environ.get("SGP_API_KEY"), # This is the default and can be omitted ) model_instance = client.models.create( account_id="account_id", model_type="COMPLETION", name="name", ) print(model_instance.id) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/stainless-sdks/sgp-go\"\n\t\"github.com/stainless-sdks/sgp-go/option\"\n)\n\nfunc main() {\n\tclient := sgp.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tmodelInstance, err := client.Models.New(context.TODO(), sgp.ModelNewParams{\n\t\tAccountID: sgp.F(\"account_id\"),\n\t\tModelType: sgp.F(sgp.ModelNewParamsModelTypeCompletion),\n\t\tName: sgp.F(\"name\"),\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", modelInstance.ID)\n}\n" components: schemas: ModelInstanceRequest: properties: name: type: string title: Name display_name: title: Display Name type: string model_vendor: $ref: '#/components/schemas/ModelVendor' model_type: $ref: '#/components/schemas/ModelType' base_model_id: title: Base Model Id type: string base_model_metadata: $ref: '#/components/schemas/BaseModelMetadata' model_creation_parameters: title: Model Creation Parameters additionalProperties: true type: object model_card: title: Model Card type: string training_data_card: title: Training Data Card type: string description: title: Description type: string model_template_id: title: Model Template Id type: string model_group_id: title: Model Group Id type: string account_id: type: string title: Account Id description: The ID of the account that owns the given entity. can_patch: false type: object required: - name - model_type - account_id title: ModelInstanceRequest ModelInstanceResponse: properties: name: type: string title: Name display_name: title: Display Name type: string model_vendor: $ref: '#/components/schemas/ModelVendor' model_type: $ref: '#/components/schemas/ModelType' base_model_id: title: Base Model Id type: string base_model_metadata: $ref: '#/components/schemas/BaseModelMetadata' model_creation_parameters: title: Model Creation Parameters additionalProperties: true type: object model_card: title: Model Card type: string training_data_card: title: Training Data Card type: string description: title: Description type: string model_template_id: title: Model Template Id type: string model_group_id: title: Model Group Id type: string id: type: string title: Id description: The unique identifier of the entity. created_at: type: string format: date-time title: Created At description: The date and time when the entity was created in ISO format. account_id: type: string title: Account Id description: The ID of the account that owns the given entity. can_patch: false created_by_user_id: type: string title: Created By User Id description: The user who originally created the entity. created_by_identity_type: $ref: '#/components/schemas/IdentifierTypeEnum' description: The type of identity that created the entity. request_schema: additionalProperties: true type: object title: Request Schema description: JSON schema for the requests to the model instance response_schema: additionalProperties: true type: object title: Response Schema description: JSON schema for the response to the model deployment_count: type: integer title: Deployment Count description: Number of deployments of this model instance supports_multi_turn: type: boolean title: Supports Multi Turn description: True if a model supports multi-turn conversations natively type: object required: - name - model_type - id - created_at - account_id - created_by_user_id - created_by_identity_type - request_schema - response_schema - deployment_count - supports_multi_turn title: ModelInstanceResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ModelVendor: type: string enum: - OPENAI - COHERE - GOOGLE - VERTEX_AI - ANTHROPIC - LAUNCH - LLMENGINE - BEDROCK - FIREWORKS_AI - OTHER title: ModelVendor description: |- An enum representing the different types of model vendors supported. Attributes: OPENAI: Denotes that the model vendor is OpenAI. COHERE: Denotes that the model vendor is Cohere. GOOGLE: Denotes that the model vendor is Google. ANTHROPIC: Denotes that the model vendor is Anthropic. LLMENGINE: Denotes that the model vendor is LLM Engine. OTHER: Denotes that the model vendor is Other. ModelType: type: string enum: - COMPLETION - CHAT_COMPLETION - AGENT - EMBEDDING - RERANKING - GENERIC - BUNDLE title: ModelType description: |- An enum representing the different types of models supported. Attributes: COMPLETION: Denotes that the model type is completion. CHAT_COMPLETION: Denotes that the model type is chat completion. AGENT: Denotes that the model type is agent. EMBEDDING: Denotes that the model type is embedding. RERANKING: Denotes that the model type is reranking. GENERIC: Denotes that the model type is generic. BUNDLE: "Not to be used directly - type to surface a model bundle in the UI - TODO: Explicitly type a bundle BaseModelMetadata: properties: ui_model_section_type: $ref: '#/components/schemas/UiModelSectionType' model_developer: title: Model Developer type: string model_license_url: title: Model License Url type: string delivery_date: title: Delivery Date type: string modelDetails: $ref: '#/components/schemas/BaseModelDetails' type: object title: BaseModelMetadata IdentifierTypeEnum: type: string enum: - user - service_account title: IdentifierTypeEnum ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context additionalProperties: true type: object required: - loc - msg - type title: ValidationError UiModelSectionType: type: string enum: - PARTNER - OPENSOURCE - CUSTOM title: UiModelSectionType BaseModelDetails: properties: number_of_parameters: title: Number Of Parameters type: integer token_context_window: title: Token Context Window type: integer languages: title: Languages type: integer alignments: title: Alignments type: integer type: object title: BaseModelDetails ````