> ## Documentation Index > Fetch the complete documentation index at: https://docs.portkey.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create Virtual Key > [!WARNING] > > **Deprecated.** Use the [Integrations API](https://docs.portkey.ai/docs/api-reference/admin-api/control-plane/integrations/create-integration.md) to store provider credentials and the [Providers API](https://docs.portkey.ai/docs/api-reference/admin-api/control-plane/providers/create-provider.md) to create AI Providers in your workspace. Existing virtual keys continue to work — no code changes needed. #### Azure OpenAI Create virtual key to access your Azure OpenAI models or deployments, and manage all auth in one place. > [accordion] Default Auth > > ```py Python theme={"system"} > from portkey_ai import Portkey > > client = Portkey( > api_key="" > ) > > virtual_key = client.virtual_keys.create( > name="Azure-Virtual-Default", > provider="azure-openai", > note="Azure Note", > key="", > resourceName="", > deploymentConfig=[ > { > "apiVersion": "2024-08-01-preview", > "deploymentName": "DeploymentName", > "is_default": True, > }, > { > "apiVersion": "2024-08-01-preview", > "deploymentName": "DeploymentNam2e", > "is_default": False, > }, > ], > ) > > print(virtual_key) > ``` > > ```ts JavaScript theme={"system"} > import Portkey from 'portkey-ai'; > > const portkey = new Portkey({ > apiKey: 'PORTKEY_API_KEY' > }); > > async function main() { > const key = await client.virtualKeys.create({ > name: "Azure-Virtual-Default", > provider: "azure-openai", > note: "Azure Note", > key: "", > resourceName: "", > deploymentConfig: [ > { > "apiVersion": "2024-08-01-preview", > "deploymentName": "DeploymentName", > "is_default": True, > }, > { > "apiVersion": "2024-08-01-preview", > "deploymentName": "DeploymentNam2e", > "is_default": False, > } > ] > }); > > console.log(key); > } > > main(); > ``` > [accordion] Azure Entra ID > > ```py Python theme={"system"} > from portkey_ai import Portkey > > client = Portkey( > api_key="" > ) > > virtual_key = client.virtual_keys.create( > name="Azure-Virtual-entra", > provider="azure-openai", > note="azure entra", > resourceName="", > deploymentConfig=[ > { > "deploymentName": "", > "is_default": True, > "apiVersion": "2024-08-01-preview", > } > ], > azureAuthMode="entra", > azureEntraClientId="", > azureEntraClientSecret="", > azureEntraTenantId="", > ) > > print(virtual_key) > ``` > > ```ts JavaScript theme={"system"} > import Portkey from 'portkey-ai'; > > const portkey = new Portkey({ > apiKey: 'PORTKEY_API_KEY' > }); > > async function main() { > const key = await client.virtualKeys.create({ > name: "Azure-Virtual-entra", > provider: "azure-openai", > note: "azure entra", > resourceName: "", > deploymentConfig: [ > { > "deploymentName": "", > "is_default": True, > "apiVersion": "2024-08-01-preview", > } > ], > azureAuthMode: "entra", > azureEntraClientId: "", > azureEntraClientSecret: "", > azureEntraTenantId: "" > }); > > console.log(key); > } > > main(); > ``` > [accordion] Azure Managed Identity > > ```py Python theme={"system"} > from portkey_ai import Portkey > > client = Portkey( > api_key="", > ) > > virtual_key = client.virtual_keys.create( > name="Azure-Virtual-entra", > provider="azure-openai", > note="azure entra", > resourceName="", > deploymentConfig=[ > { > "deploymentName": "", > "is_default": True, > "apiVersion": "2024-08-01-preview", > } > ], > azureAuthMode="managed", > azureManagedClientId="" # optional > ) > > print(virtual_key) > ``` > > ```ts JavaScript theme={"system"} > import Portkey from 'portkey-ai'; > > const portkey = new Portkey({ > apiKey: 'PORTKEY_API_KEY' > }); > > async function main() { > const key = await client.virtualKeys.create({ > name="Azure-Virtual-entra", > provider="azure-openai", > note="azure entra", > resourceName="", > deploymentConfig=[ > { > "deploymentName": "", > "is_default": True, > "apiVersion": "2024-08-01-preview", > } > ], > azureAuthMode="managed", > azureManagedClientId="" # optional > }); > > console.log(key); > } > > main(); > ``` #### AWS Bedrock Create virtual key to access your AWS Bedrock models or deployments, and manage all auth in one place. > [accordion] AWS Assumed Role > > ```py Python theme={"system"} > from portkey_ai import Portkey > > client = Portkey( > api_key="", > ) > > virtual_key = client.virtual_keys.create( > name="bedrock-assumed", > provider="bedrock", > note="bedrock", > awsRegion="", > awsAuthType="assumedRole", > awsRoleArn="arn:aws:iam:::role/", > awsExternalId="", > ) > > print(virtual_key) > ``` > > ```ts JavaScript theme={"system"} > import Portkey from 'portkey-ai'; > > const portkey = new Portkey({ > apiKey: 'PORTKEY_API_KEY' > }); > > async function main() { > const key = await client.virtualKeys.create({ > name: "bedrock-assumed", > provider: "bedrock", > note: "bedrock", > awsRegion: "", > awsAuthType: "assumedRole", > awsRoleArn: "arn:aws:iam:::role/", > awsExternalId: "" > }); > > console.log(key); > } > > main(); > ``` #### Vertex AI Create virtual key to access any models available or hosted on Vertex AI. [Docs →](https://docs.portkey.ai/docs/integrations/llms/vertex-ai.md) > [card] [Model Catalog](https://docs.portkey.ai/docs/product/model-catalog.md) > > Manage AI providers and models centrally with budget limits, rate limits, and model provisioning. *** > [card] [Portkey is now PRISMA AIRS AI Gateway. See it in action.](https://www.paloaltonetworks.in/ai-security/ai-gateway?utm_source=portkey\&utm_medium=referral\&utm_campaign=prisma_airs\&utm_content=docs_nav#contact) > > Contact Us ## OpenAPI ````yaml post /virtual-keys openapi: 3.0.0 info: title: Portkey API description: >- The Portkey REST API. Please see https://portkey.ai/docs/api-reference for more details. version: 2.0.0 termsOfService: https://portkey.ai/terms contact: name: Portkey Developer Forum url: https://portkey.wiki/community license: name: MIT url: https://github.com/Portkey-AI/portkey-openapi/blob/master/LICENSE servers: - url: https://api.portkey.ai/v1 description: Portkey API Public Endpoint security: - Portkey-Key: [] tags: - name: Assistants description: Build Assistants that can call models and use tools. - name: Audio description: Turn audio into text or text into audio. - name: Chat description: >- Given a list of messages comprising a conversation, the model will return a response. - name: Messages description: >- Anthropic-native Messages API. Send a structured list of input messages and receive a response. Supported on Anthropic, AWS Bedrock, Google Vertex AI, and Azure AI Foundry (Anthropic models). - name: Realtime description: WebSocket proxy for provider Realtime APIs - name: Collections description: Create, List, Retrieve, Update, and Delete collections of prompts. - name: Labels description: Create, List, Retrieve, Update, and Delete labels. - name: Prompt Collections description: Create, List, Retrieve, Update, and Delete prompt collections. - name: PromptPartials description: Create, List, Retrieve, Update, and Delete prompt partials. - name: Prompts description: >- Given a prompt template ID and variables, will run the saved prompt template and return a response. - name: Guardrails description: >- Create, List, Retrieve, Update, and Delete Guardrails for LLM requests and MCP tool calls. Includes endpoints to map guardrails to MCP servers. - name: Completions description: >- Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position. - name: Embeddings description: >- Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. - name: Rerank description: >- Rerank a list of documents based on their relevance to a query. Supported providers include Cohere, Voyage, Jina, Pinecone, Bedrock, and Azure AI. - name: OCR description: >- Extract text and structured content from documents (PDFs and images) using OCR models. Supported providers include Mistral AI and Azure AI Foundry. - name: Fine-tuning description: Manage fine-tuning jobs to tailor a model to your specific training data. - name: Batch description: Create large batches of API requests to run asynchronously. - name: Files description: >- Files are used to upload documents that can be used with features like Assistants and Fine-tuning. - name: Images description: Given a prompt and/or an input image, the model will generate a new image. - name: Models description: List and describe the various models available in the API. - name: Moderations description: >- Given a input text, outputs if the model classifies it as potentially harmful. - name: Configs description: Create, List, Retrieve, and Update your Portkey Configs. - name: Feedback description: Send and Update any feedback. - name: Logs description: Custom Logger to add external logs to Portkey. - name: Integrations description: Create, List, Retrieve, Update, and Delete your Portkey Integrations. - name: Integrations > Workspaces description: Manage workspace access for your Portkey Integrations. - name: Integrations > Models description: Manage model access for your Portkey Integrations. - name: Providers description: Create, List, Retrieve, Update, and Delete your Portkey Providers. - name: Virtual-keys description: Create, List, Retrieve, Update, and Delete your Portkey Virtual keys. - name: Users description: Create and manage users. - name: User-invites description: Create and manage user invites. - name: Workspaces description: Create and manage workspaces. - name: Workspaces > Members description: Create and manage workspace members. - name: MCP Integrations description: Create, List, Retrieve, Update, and Delete MCP Integrations. - name: MCP Integrations > Workspaces description: Manage workspace access for MCP Integrations. - name: MCP Integrations > Capabilities description: List and manage capabilities for MCP Integrations. - name: MCP Integrations > Metadata description: Get MCP Integration metadata and sync info. - name: MCP Servers description: >- Create, List, Retrieve, Update, and Delete MCP Servers (workspace instances of MCP Integrations). - name: MCP Servers > Capabilities description: List and manage capabilities for MCP Servers. - name: MCP Servers > User Access description: List and manage user access for MCP Servers. - name: MCP Servers > Connections description: List and manage user connections for MCP Servers. - name: Api-Keys description: Create, List, Retrieve, Update, and Delete your Portkey API keys. - name: Logs Export description: Exports logs service. - name: Audit Logs description: Get audit logs for your Portkey account. - name: Analytics description: >- Get analytics over different data points like requests, costs, tokens, etc. - name: Analytics > Graphs description: Get data points for graphical representation. - name: Analytics > Summary description: Get overall summary for the selected time bucket. - name: Analytics > Groups description: Get grouped metrics for the selected time bucket. - name: Usage Limits Policies description: Manage usage limits policies to control total usage over time - name: Rate Limits Policies description: Manage rate limits policies to control request or token rates - name: Access Policies description: >- Manage access policies that allow or deny users, groups, and agents access to MCP servers and providers - name: Model Pricing description: Model pricing configurations for 2300+ LLMs across 40+ providers - name: Secret-References description: >- Create, List, Retrieve, Update, and Delete secret references to external secret managers. - name: Deployments description: >- Register, List, Retrieve, Update, and Delete self-hosted Gateway deployments. - name: Egress-Allowlist description: >- Create, List, Retrieve, Update, and Delete organisation egress allowlist entries trusted as custom hosts. paths: /virtual-keys: servers: - url: https://api.portkey.ai/v1 description: Portkey API Public Endpoint - url: SELF_HOSTED_CONTROL_PLANE_URL description: Self-Hosted Control Plane URL post: tags: - Virtual-keys summary: Create a Virtual Key requestBody: required: true content: application/json: schema: type: object properties: name: type: string provider: type: string enum: - openai - azure-openai - ai21 - anthropic - anyscale - azure-openai - bedrock - cohere - deepinfra - fireworks-ai - google - groq - hugging-face - jina - lingyi - mistral-ai - monsterapi - moonshot - nomic - novita-ai - open-ai - openrouter - palm - perplexity-ai - predibase - reka-ai - segmind - stability-ai - together-ai - vertex-ai - workers-ai - zhipu key: type: string note: type: string nullable: true apiVersion: type: string nullable: true resourceName: type: string nullable: true deploymentName: type: string nullable: true workspace_id: type: string format: uuid description: optional, needed when using organisation admin API keys deploymentConfig: type: array items: type: object properties: apiVersion: type: string alias: type: string is_default: type: boolean deploymentName: type: string required: - apiVersion - deploymentName usage_limits: $ref: '#/components/schemas/UsageLimits' rate_limits: $ref: '#/components/schemas/RateLimits' expires_at: type: string format: date-time secret_mappings: type: array items: $ref: '#/components/schemas/SecretMapping' description: >- Dynamically resolve secrets from secret references at runtime. Valid target_field values are "key" or "model_config." (e.g. "model_config.awsSecretAccessKey"). Each target_field must be unique. When "key" is mapped, the key field becomes optional. examples: generic: value: name: My first virtual key provider: openai key: sk-jhkfkjs8d9f7jksfghkjhfg note: Virtual key description usage_limits: credit_limit: 10 periodic_reset: monthly alert_threshold: 9 workspace_id: '' azure-openai: value: provider: azure-openai key: openai-test name: Key 1 Azure Open AI note: description deploymentConfig: - apiVersion: a alias: b deploymentName: c is_default: true - apiVersion: a alias: b deploymentName: c is_default: false resourceName: c bedrock: value: provider: bedrock key: openai-test name: Bedrock Key note: description awsAccessKeyId: a awsSecretAccessKey: b awsRegion: c vertex-ai: value: provider: vertex-ai key: vertex test name: Vertex AI Key note: description vertexProjectId: a vertexRegion: b workers-ai: value: provider: vertex-ai key: cloudflare test name: CF Workers AI Key note: description workersAiAccountId: a responses: '200': description: Successful response content: application/json: schema: type: object properties: success: type: boolean data: type: object properties: slug: type: string '401': description: Unauthorized response content: application/json: schema: type: object properties: success: type: boolean data: type: object properties: message: type: string example: success: false data: message: Unauthorised Request x-code-samples: - lang: python label: Default source: | from portkey_ai import Portkey # Initialize the Portkey client portkey = Portkey( api_key="PORTKEY_API_KEY", ) # Add a new virtual key new_virtual_key = portkey.virtual_keys.create( name="openaiVKey", provider="openai", key="PROVIDER_API_KEY" ) print(new_virtual_key) - lang: javascript label: Default source: | import { Portkey } from "portkey-ai"; const portkey = new Portkey({ apiKey: "PORTKEY_API_KEY", }) const newVkey=await portkey.virtualKeys.create({ name:"openaiVKey", provider:"openai", key:"PROVIDER_API_KEY", }) console.log(newVkey); - lang: curl label: Default source: | curl -X POST https://api.portkey.ai/v1/virtual-keys \ -H "x-portkey-api-key: PORTKEY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "openaiVKey", "provider": "openai", "key": "PROVIDER_API_KEY" }' - lang: python label: Self-Hosted source: | from portkey_ai import Portkey # Initialize the Portkey client portkey = Portkey( api_key="PORTKEY_API_KEY", base_url="SELF_HOSTED_CONTROL_PLANE_URL" ) # Add a new virtual key new_virtual_key = portkey.virtual_keys.create( name="openaiVKey", provider="openai", key="PROVIDER_API_KEY" ) print(new_virtual_key) - lang: javascript label: Self-Hosted source: | import { Portkey } from "portkey-ai"; const portkey = new Portkey({ apiKey: "PORTKEY_API_KEY", baseUrl: "SELF_HOSTED_CONTROL_PLANE_URL" }) const newVkey=await portkey.virtualKeys.create({ name:"openaiVKey", provider:"openai", key:"PROVIDER_API_KEY", }) console.log(newVkey); - lang: curl label: Self-Hosted source: | curl -X POST SELF_HOSTED_CONTROL_PLANE_URL/virtual-keys \ -H "x-portkey-api-key: PORTKEY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "openaiVKey", "provider": "openai", "key": "PROVIDER_API_KEY" }' components: schemas: UsageLimits: type: object properties: credit_limit: type: integer description: Credit Limit. Used for tracking usage minimum: 1 default: null type: type: string description: Type of credit limit enum: - cost - tokens alert_threshold: type: integer description: Alert Threshold. Used for alerting when usage reaches more than this minimum: 1 default: null periodic_reset: type: string description: Reset the usage periodically. enum: - monthly - weekly nullable: true example: monthly periodic_reset_days: type: integer description: >- Reset the usage counter every N days (1-365). Mutually exclusive with periodic_reset. minimum: 1 maximum: 365 nullable: true example: 30 next_usage_reset_at: type: string format: date-time description: >- ISO 8601 datetime for the next scheduled usage reset. Auto-computed from periodic_reset or periodic_reset_days if not provided. nullable: true example: '2026-05-01T00:00:00Z' example: credit_limit: 10 periodic_reset: monthly alert_threshold: 8 RateLimits: type: object properties: type: type: string enum: - requests - tokens unit: type: string enum: - rpd - rph - rpm value: type: integer SecretMapping: type: object required: - target_field - secret_reference_id properties: target_field: type: string description: > The field on the entity to populate from the secret reference. Must be unique within the array. - **Integrations**: `key` or `configurations.` (e.g. `configurations.aws_secret_access_key`) - **Virtual Keys**: `key` or `model_config.` (e.g. `model_config.awsSecretAccessKey`) - **MCP Integrations**: `configurations.` (e.g. `configurations.oauth_metadata`) example: key secret_reference_id: type: string description: >- UUID or slug of the secret reference. Must belong to the same organisation and be accessible by the workspace. example: my-aws-secret secret_key: type: string nullable: true description: >- Override the secret_key defined on the secret reference. Use to pick a specific key from a multi-value secret. value_format: type: string nullable: true enum: - json - string description: > Format of the secret value. - `string`: The secret value is treated as a plain string. - `json`: The secret value is parsed as JSON before being applied to the target field. Use this when the target field expects a structured object (e.g. `configurations.oauth_metadata`). example: json securitySchemes: Portkey-Key: type: apiKey in: header name: x-portkey-api-key ```` ## Related topics - [Upgrade to Model Catalog](https://docs.portkey.ai/docs/support/upgrade-to-model-catalog.md) - [December](https://docs.portkey.ai/docs/changelog/2024/dec.md) - [Virtual Keys](https://docs.portkey.ai/docs/product/ai-gateway/virtual-keys.md) - [Retrieve Virtual Key](https://docs.portkey.ai/docs/api-reference/admin-api/control-plane/virtual-keys/retrieve-virtual-key.md) - [Update Virtual Key](https://docs.portkey.ai/docs/api-reference/admin-api/control-plane/virtual-keys/update-virtual-key.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.