> ## Documentation Index > Fetch the complete documentation index at: https://developer.instantly.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create AI enrichment > Create an AI enrichment for a resource (list or campaign) Requires one of the following scopes: `supersearch_enrichments:create`, `supersearch_enrichments:all`, `all:create`, `all:all` ## OpenAPI ````yaml https://api.instantly.ai/openapi/api_v2.json post /api/v2/supersearch-enrichment/ai openapi: 3.1.0 info: title: API Explorer description: >- The entire API V2 documentation is interactive and can be tested here. To the right side of every endpoint you will see a box with an example request. You can click on the "Try it" button to send a request to the server right from the docs. You will need to provide an API key by clicking the `ApiKeyAuth_token` blue text. version: 2.0.0 servers: - url: https://api.instantly.ai description: Instantly API Server security: - ApiKeyAuth: [] tags: - name: Analytics description: Endpoints related to analytics x-displayName: Analytics - name: OAuth description: >- OAuth authentication endpoints for connecting Google and Microsoft email accounts x-displayName: OAuth - name: Account description: An email account that can be used to send campaigns x-displayName: Account - name: Campaign description: A campaign that can be sent to a list of recipients x-displayName: Campaign - name: Email description: >- A campaign email, a reply, a manually sent email, or any other email that's visible in the Unibox x-displayName: Email - name: EmailVerification description: A single email verification x-displayName: Email Verification - name: LeadList description: A list used to store leads x-displayName: Lead List - name: InboxPlacementTest description: An inbox placement test x-displayName: Inbox Placement Test - name: InboxPlacementAnalytics description: Analytics data for individual emails in inbox placement tests x-displayName: Inbox Placement Analytics - name: InboxPlacementBlacklist&SpamAssassinReport description: Report data for an inbox placement test x-displayName: Inbox Placement Blacklist & SpamAssassin Report - name: APIKey description: API Key x-displayName: API Key - name: AccountCampaignMapping description: Account Campaign Mapping x-displayName: Account Campaign Mapping - name: Lead description: A lead entity representing an individual lead x-displayName: Lead - name: BackgroundJob description: A background job that can be used to perform long-running tasks x-displayName: Background Job - name: CustomTag description: >- A custom tag for organizing and categorizing accounts and campaigns. You can use them as filters in apis that list accounts and campaigns. x-displayName: Custom Tag - name: CustomTagMapping description: >- This entity represents a tag being assigned to a specific campaign or email account. When an email account is assigned a tag, a new custom tag mapping entry is created, which connects the tag (`tag_id` field) with the email account (`resource_id` field). You can use it to see which tag si connected to which resource. x-displayName: Custom Tag Mapping - name: BlockListEntry description: A blocked email or domain x-displayName: Block List Entry - name: LeadLabel description: A custom label for categorizing and managing leads x-displayName: Lead Label - name: Workspace description: A workspace entity representing a workspace x-displayName: Workspace - name: SuperSearchEnrichment description: >- An enrichment can take different forms, such as email enrichment or LinkedIn enrichment. Leads may be imported from SuperSearch using the dedicated endpoint, or enriched directly within a list or campaign by attaching an enrichment to it. x-displayName: SuperSearch Enrichment - name: WorkspaceGroupMember description: >- A member of a workspace group. You can use the endpoints within this entity to manage the members of a workspace group. x-displayName: Workspace Group Member - name: WorkspaceMember description: A member of a workspace with associated user details x-displayName: Workspace Member - name: CampaignSubsequence description: A subsequence entity representing a follow-up sequence x-displayName: Campaign Subsequence - name: AuditLog description: Audit log records for tracking system activities x-displayName: Audit Log - name: Webhook description: A webhook subscription for receiving event notifications x-displayName: Webhook - name: WebhookEvent description: A webhook event that was sent or attempted to be sent x-displayName: Webhook Event - name: DFYEmailAccountOrder description: A Done-For-You email account order x-displayName: DFY Email Account Order - name: CustomPromptTemplate description: Custom prompt templates for creating custom prompts x-displayName: Custom Prompt Template - name: SalesFlow description: >- Manages how sales users view and interact with campaign and lead lists within the sales flow. x-displayName: Sales Flow - name: EmailTemplate description: A campaign email template x-displayName: Email Template - name: WorkspaceBilling description: Workspace Billing x-displayName: Workspace Billing - name: CRMActions description: CRM related actions x-displayName: CRM Actions paths: /api/v2/supersearch-enrichment/ai: post: tags: - SuperSearchEnrichment summary: Create AI enrichment description: >- Create an AI enrichment for a resource (list or campaign) Requires one of the following scopes: `supersearch_enrichments:create`, `supersearch_enrichments:all`, `all:create`, `all:all` operationId: createAIEnrichment requestBody: content: application/json: schema: type: object required: - resource_id - output_column - resource_type - model_version properties: resource_id: type: string format: uuid description: Id of the resource (list or campaign) to enrich example: 01234567-89ab-cdef-0123-456789abcdef output_column: type: string description: >- Name of the column where the AI enrichment results will be stored example: ai_generated_content resource_type: type: number enum: - 1 - 2 x-enumDescriptions: '1': Campaign '2': List description: Type of the entity to enrich example: 2 input_columns: type: array items: type: string example: first_name description: >- List of column names to use as input data for the AI enrichment. These are the fields from your leads that will be used to generate content. model_version: type: string enum: - '3.5' - '4.0' - gpt-4o - o3 - gpt-4.1 - gpt-4.1-mini - gpt-5-mini - gpt-5-nano - gpt-5 - gpt-5.4 - claude-3.7-sonnet - claude-3.5-sonnet - claude-4.5-sonnet - r1 - grok-4 - gemini-2.0-flash - gemini-3.0-flash - gemini-3.0-pro - sonar - sonar-pro - instantly-ai-lightspeed-agent-for-web-research - instantly-ai-lightspeed-agent-for-email-generation x-enumDescriptions: '3.5': >- GPT-3.5 Turbo - OpenAI's standard model with good performance and low cost gpt-5: >- GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. gpt-5.4: >- GPT-5.4 is the latest generation non-reasoning model, optimized for fast, high-quality responses at low latency. gpt-5-mini: >- GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. gpt-5-nano: >- GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. '4.0': GPT-4 - OpenAI's advanced model with improved reasoning gpt-4o: >- GPT-4o - OpenAI's optimized model with improved performance o3: >- o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. gpt-4.1: >- GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. gpt-4.1-mini: >- GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. claude-3.7-sonnet: Claude 3.7 Sonnet - Anthropic's most capable model claude-3.5-sonnet: Claude 3.5 Sonnet - Anthropic's balanced model claude-4.5-sonnet: >- Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model to date, optimized for real-world agents and coding workflows. r1: R1 - Deepseek's advanced chat model grok-4: Grok 4 - X AI's latest reasoning model gemini-2.0-flash: Gemini 2.0 Flash - Google's powerful and versatile model gemini-3.0-flash: >- Gemini 3.0 Flash - Is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance gemini-3.0-pro: >- Gemini 3.0 Pro - Google's latest model with improved capabilities sonar: >- Sonar - Perplexity's lightweight, affordable, fast, and simple to use model. sonar-pro: Sonar Pro - Perplexity's most advanced model. instantly-ai-lightspeed-agent-for-web-research: Instantly AI - LightSpeed Agent for Web Research instantly-ai-lightspeed-agent-for-email-generation: Instantly AI - LightSpeed Agent for Email Generation description: >- Version of the AI model to use for enrichment. Different models have different capabilities, costs, and token limits. example: gpt-4o use_instantly_account: type: boolean description: >- When true, the enrichment will use Instantly's account for API calls. When false, it will use your own API keys configured in settings. example: true overwrite: type: boolean description: >- When true, will overwrite existing values in the output column. When false, only empty fields will be enriched. example: false auto_update: type: boolean description: >- When true, new leads added to the campaign/list will be automatically enriched using these same settings. example: true skip_leads_without_email: type: boolean description: When true, leads without an email will be skipped. example: false limit: type: number description: Maximum number of leads to enrich. minimum: 1 maximum: 1000000 example: 100 prompt: type: string description: >- Custom prompt to guide the AI enrichment. Use {{variables}} to reference input data. Only used when templateId is not provided. example: >- Write a personalized email to {{first_name}} from {{company_name}} about our new product template_id: type: string description: >- ID of a predefined AI prompt template to use instead of a custom prompt. Templates are reusable prompt configurations. example: '123' status: type: number enum: - 1 - 2 - 3 - 4 x-enumDescriptions: '1': Job is pending processing '2': Job is currently being processed '3': Job has been completed successfully '4': Job processing failed description: Status of the job example: 1 filters: type: array items: type: object properties: {} description: Filters to apply to the enrichment example: column_name: email type: 1 value: - test@test.com required: true responses: '200': description: Default Response content: application/json: schema: type: object properties: id: type: string description: Unique identifier for the enrichment example: 01234567-89ab-cdef-0123-456789abcdef resource_id: type: string format: uuid description: ID of the resource being enriched example: 01234567-89ab-cdef-0123-456789abcdef resource_type: type: number description: Type of the resource (1 for Campaign, 2 for List) enum: - CAMPAIGN - LIST - 1 - 2 x-enumDescriptions: '1': Campaign '2': List example: 1 output_column: type: string description: Name of the column where results will be stored example: ai_generated_content status: type: number description: Status of the enrichment job example: 1 model_version: type: string description: AI model version used for enrichment example: gpt-4o input_columns: type: array items: type: string example: first_name description: Input columns used for enrichment overwrite: type: boolean description: Whether to overwrite existing data example: false auto_update: type: boolean description: Whether to auto-update new leads example: true limit: type: number description: Maximum number of leads to process example: 100 template_id: type: - 'null' - string description: ID of the prompt template used example: '15762598695796759' required: - id - resource_id - resource_type - output_column - status - model_version - overwrite - auto_update additionalProperties: false '401': description: >- This request is unauthorized (either the Authorization header is missing or invalid, or the API key has been revoked) content: application/json: schema: type: object properties: statusCode: type: number enum: - 401 example: 401 error: type: string enum: - Unauthorized example: Unauthorized message: type: string example: Missing Authorization header required: - statusCode - error - message '402': description: >- This request cannot be fulfilled because the workspace does not have an active paid plan content: application/json: schema: type: object properties: statusCode: type: number enum: - 402 example: 402 error: type: string enum: - Payment Required example: Payment Required message: type: string example: Workspace does not have an active paid plan required: - statusCode - error - message '404': description: The requested resource was not found content: application/json: schema: type: object properties: statusCode: type: number enum: - 404 example: 404 error: type: string enum: - Not Found example: Not Found message: type: string example: Resource not found required: - statusCode - error - message '429': description: >- You have exceeded the rate limit. Please check the rate limit docs for more information. content: application/json: schema: type: object properties: statusCode: type: number enum: - 429 example: 429 error: type: string enum: - Too Many Requests example: Too Many Requests message: type: string example: Rate limit exceeded required: - statusCode - error - message components: securitySchemes: ApiKeyAuth: type: http scheme: bearer ````