> ## Documentation Index > Fetch the complete documentation index at: https://portkey-docs-add-third-party-integration-issues-fixes.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Retrieve Integration ## OpenAPI ````yaml get /integrations/{slug} 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: 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 prompt Guardrails. - 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: 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: 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. paths: /integrations/{slug}: servers: - url: https://api.portkey.ai/v1 description: Portkey API Public Endpoint - url: SELF_HOSTED_CONTROL_PLANE_URL description: Self-Hosted Control Plane URL get: tags: - Integrations summary: Get a Integration parameters: - name: slug in: path required: true schema: type: string responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/IntegrationDetailResponse' x-code-samples: - lang: python label: Default source: | from portkey_ai import Portkey # Initialize the Portkey client portkey = Portkey( api_key="PORTKEY_API_KEY", ) # Get a specific virtual key virtual_key = portkey.virtual_keys.retrieve( slug='VIRTUAL_KEY_SLUG' ) print(virtual_key) - lang: javascript label: Default source: | import { Portkey } from "portkey-ai"; const portkey = new Portkey({ apiKey: "PORTKEY_API_KEY", }) const vKey=await portkey.virtualKeys.retrieve({ slug:'VIRTUAL_KEY_SLUG' }) console.log(vKey); - lang: curl label: Default source: > curl -X GET https://api.portkey.ai/v1/virtual-keys/VIRTUAL_KEY_SLUG \ -H "x-portkey-api-key: PORTKEY_API_KEY" - lang: curl label: Self-Hosted source: > curl -X GET SELF_HOSTED_CONTROL_PLANE_URL/virtual-keys/VIRTUAL_KEY_SLUG \ -H "x-portkey-api-key: PORTKEY_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" ) # Get a specific virtual key virtual_key = portkey.virtual_keys.retrieve( slug='VIRTUAL_KEY_SLUG' ) print(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 vKey=await portkey.virtualKeys.retrieve({ slug:'VIRTUAL_KEY_SLUG' }) console.log(vKey); components: schemas: IntegrationDetailResponse: allOf: - $ref: '#/components/schemas/IntegrationList' - type: object properties: masked_key: type: string description: Masked API key configurations: type: object description: > Provider-specific configuration object **⚠️ Security Note - Response Masking:** When retrieving integration details, sensitive fields are automatically masked: - Sensitive fields get a `masked_` prefix (e.g., `client_secret` → `masked_client_secret`) - Non-sensitive fields (IDs, URLs, regions, etc.) remain unchanged oneOf: - $ref: '#/components/schemas/OpenAIConfiguration' title: OpenAI - $ref: '#/components/schemas/AzureOpenAIConfiguration' title: Azure OpenAI - $ref: '#/components/schemas/BedrockConfiguration' title: AWS Bedrock - $ref: '#/components/schemas/VertexAIConfiguration' title: Vertex AI - $ref: '#/components/schemas/AzureAIConfiguration' title: Azure AI - $ref: '#/components/schemas/WorkersAIConfiguration' title: Workers AI - $ref: '#/components/schemas/SageMakerConfiguration' title: AWS Sagemaker - $ref: '#/components/schemas/HuggingFaceConfiguration' title: Hugginface - $ref: '#/components/schemas/CortexConfiguration' title: Cortex - $ref: '#/components/schemas/CustomHostConfiguration' title: Custom Base URL global_workspace_access_settings: $ref: '#/components/schemas/GlobalWorkspaceAccess' type: object nullable: true description: Global workspace access configuration allow_all_models: type: boolean description: Whether new models will be enabled by default workspace_count: type: integer description: Number of workspaces with access to this integration secret_mappings: type: array items: $ref: '#/components/schemas/SecretMapping' description: >- Secret reference mappings for this integration. Valid target_field values are "key" or "configurations.". pricing_adjustments: $ref: '#/components/schemas/PricingAdjustments' IntegrationList: type: object properties: id: type: string format: UUID organisation_id: type: string format: UUID ai_provider_id: type: string name: type: string status: type: string enum: - active - archived created_at: type: string format: date-time last_updated_at: type: string format: date-time nullable: true slug: type: string description: type: string object: type: string enum: - integration OpenAIConfiguration: type: object properties: openai_organization: type: string description: OpenAI organization ID openai_project: type: string description: OpenAI project ID AzureOpenAIConfiguration: type: object required: - azure_resource_name - azure_deployment_config - azure_auth_mode properties: azure_auth_mode: type: string enum: - default - entra - managed description: Authentication mode for Azure azure_resource_name: type: string description: Azure OpenAI resource name azure_deployment_config: type: array minItems: 1 items: $ref: '#/components/schemas/AzureDeploymentConfig' azure_entra_tenant_id: type: string description: Azure AD tenant ID (required for entra auth) azure_entra_client_id: type: string description: Azure AD client ID (required for entra auth) azure_entra_client_secret: type: string description: Azure AD client secret (required for entra auth) azure_managed_client_id: type: string description: Managed identity client ID (optional for managed auth) BedrockConfiguration: type: object required: - aws_auth_type - aws_region properties: aws_auth_type: type: string enum: - accessKey - assumedRole description: AWS authentication type aws_region: type: string description: AWS region aws_access_key_id: type: string description: AWS access key ID (required for accessKey auth) aws_secret_access_key: type: string description: AWS secret access key (required for accessKey auth) aws_role_arn: type: string description: AWS role ARN (required for assumedRole auth) aws_external_id: type: string nullable: true description: AWS external ID (optional for assumedRole auth) VertexAIConfiguration: type: object required: - vertex_auth_type - vertex_region properties: vertex_auth_type: type: string enum: - basic - serviceAccount description: Vertex AI authentication type vertex_region: type: string description: GCP region vertex_project_id: type: string description: GCP project ID (required for basic auth) vertex_service_account_json: type: object description: Service account JSON (required for serviceAccount auth) AzureAIConfiguration: type: object required: - azure_foundry_url - azure_auth_mode properties: azure_auth_mode: type: string enum: - default - entra - managed description: Authentication mode for Azure AI azure_foundry_url: type: string description: Azure AI Foundry URL azure_api_version: type: string maxLength: 30 description: Azure API version azure_deployment_name: type: string description: Azure deployment name azure_entra_tenant_id: type: string description: Azure AD tenant ID (required for entra auth) azure_entra_client_id: type: string description: Azure AD client ID (required for entra auth) azure_entra_client_secret: type: string description: Azure AD client secret (required for entra auth) azure_managed_client_id: type: string description: Managed identity client ID (optional for managed auth) WorkersAIConfiguration: type: object required: - workers_ai_account_id properties: workers_ai_account_id: type: string description: Cloudflare Workers AI account ID SageMakerConfiguration: allOf: - $ref: '#/components/schemas/BedrockConfiguration' - type: object properties: amzn_sagemaker_custom_attributes: type: string description: Custom attributes for SageMaker amzn_sagemaker_target_model: type: string description: Target model for SageMaker amzn_sagemaker_target_variant: type: string description: Target variant for SageMaker amzn_sagemaker_target_container_hostname: type: string description: Target container hostname amzn_sagemaker_inference_id: type: string description: Inference ID amzn_sagemaker_enable_explanations: type: string description: Enable explanations amzn_sagemaker_inference_component: type: string description: Inference component amzn_sagemaker_session_id: type: string description: Session ID amzn_sagemaker_model_name: type: string description: Model name HuggingFaceConfiguration: type: object properties: huggingface_base_url: type: string description: Custom Hugging Face base URL CortexConfiguration: type: object required: - snowflake_account properties: snowflake_account: type: string description: Snowflake account identifier CustomHostConfiguration: type: object properties: custom_host: type: string description: >- Custom host URL (can be used along with other provider specific configuration fields) custom_headers: type: object additionalProperties: type: string description: >- Custom headers to send with requests (can be used along with other provider specific configuration fields) GlobalWorkspaceAccess: type: object required: - enabled properties: enabled: type: boolean description: >- Whether global workspace access is enabled. When enabled, the integration will be enabled for all workspaces that are created in future. usage_limits: type: array nullable: true maxItems: 1 items: $ref: '#/components/schemas/UsageLimits' rate_limits: type: array nullable: true maxItems: 1 items: $ref: '#/components/schemas/RateLimits' 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 PricingAdjustments: type: object nullable: true additionalProperties: false description: > Per-Integration pricing adjustments applied on top of Portkey's base model pricing for cost tracking, analytics, and budget limits. Use to reflect negotiated discounts, committed-use rates, or internal markups for cost showback. properties: multiplier: $ref: '#/components/schemas/PricingMultiplier' example: multiplier: default: 0.8 cache_read_input_token: 0.9 cache_write_input_token: 0.9 AzureDeploymentConfig: type: object required: - azure_api_version - azure_deployment_name - azure_model_slug properties: alias: type: string description: Alias for the deployment azure_api_version: type: string maxLength: 30 description: Azure API version azure_deployment_name: type: string description: Azure deployment name is_default: type: boolean default: false description: Whether this is the default deployment azure_model_slug: type: string description: Azure model slug 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 PricingMultiplier: type: object additionalProperties: false description: > Multipliers applied to the corresponding pricing keys from [Portkey Models](https://portkey.ai/models). A multiplier of `1` leaves pricing unchanged, `0.8` applies a 20% discount, `1.2` applies a 20% markup. Missing or `null` fields inherit from `default`; if `default` is also unset, no change is applied. All values must be non-negative numbers. properties: default: type: number nullable: true minimum: 0 description: >- Multiplier applied to every token type unless a more specific multiplier is set. request_token: type: number nullable: true minimum: 0 description: Multiplier for input/request token cost. response_token: type: number nullable: true minimum: 0 description: Multiplier for output/response token cost. cache_read_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-read input token cost. cache_write_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-write input token cost. cache_read_audio_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-read audio input token cost. request_audio_token: type: number nullable: true minimum: 0 description: Multiplier for audio input token cost. response_audio_token: type: number nullable: true minimum: 0 description: Multiplier for audio output token cost. reasoning_token: type: number nullable: true minimum: 0 description: Multiplier for reasoning/thinking token cost. prediction_accepted_token: type: number nullable: true minimum: 0 description: Multiplier for accepted predicted-output token cost. prediction_rejected_token: type: number nullable: true minimum: 0 description: Multiplier for rejected predicted-output token cost. request_image_token: type: number nullable: true minimum: 0 description: Multiplier for image-modality input token cost. response_image_token: type: number nullable: true minimum: 0 description: Multiplier for image-modality output token cost. request_text_token: type: number nullable: true minimum: 0 description: Multiplier for text-modality input token cost. response_text_token: type: number nullable: true minimum: 0 description: Multiplier for text-modality output token cost. cache_read_image_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-read image-input token cost. cache_read_text_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-read text-input token cost. cache_write_text_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-write text-input token cost. cache_write_image_input_token: type: number nullable: true minimum: 0 description: Multiplier for cache-write image-input token cost. image: type: object nullable: true additionalProperties: false description: Image generation pricing multipliers. properties: default: type: number nullable: true minimum: 0 description: >- Multiplier applied to image generation pricing across all qualities and sizes. additional_units: type: object nullable: true description: > Multipliers for per-unit charges such as `web_search`, `file_search`, `input_image`, `input_video_standard`. Keys must match those returned by Portkey Models for the provider. additionalProperties: type: number nullable: true minimum: 0 securitySchemes: Portkey-Key: type: apiKey in: header name: x-portkey-api-key ````