Snowflake

Cortex Embed API

The Snowflake Cortex Embed API is a REST API that performs LLM embedding for input text, similar to the Snowflake Cortex EMBED_TEXT functions.

Documentation GitHub OpenAPI

Business capability

Artificial Intelligence Management BC-610.60

Operations 1

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /api/v2/cortex/inference:embed Generate text embeddings · Perform LLM embed #

Ask an LLM

“How do I turn text into vector embeddings with Snowflake Cortex?”

“Which embedding models can I choose, like the 768 or 1024 dimension ones?”

Tell an agent

Embed the text {text} using model {model}.

Generate {model} embeddings for {text} on provisioned throughput {provisioned_throughput_id}.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/snowflake:cortex-embed-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: Cortex Embed API
  description: OpenAPI 3.0 specification for the Cortex Embed REST API
  version: 0.1.0
  contact:
    name: Snowflake, Inc.
    url: https://snowflake.com
    email: support@snowflake.com
security:
- KeyPair: []
- ExternalOAuth: []
- SnowflakeOAuth: []
- ProgrammaticAccessToken: []
tags:
- name: cortex-embed
paths:
  /api/v2/cortex/inference:embed:
    post:
      summary: Perform LLM embed
      tags:
      - cortex-embed
      description: 'Perform LLM embedding for input text, similar to the Snowflake Cortex `EMBED_TEXT` functions.

        For more details on available functions, see:

        - EMBED_TEXT_768

        - EMBED_TEXT_1024'
      operationId: embed
      requestBody:
        description: Request payload containing model identifier and input text.
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EmbedRequest'
      responses:
        '200':
          description: OK - Successfully generated embeddings.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbedResponse'
        '400':
          $ref: common.yaml#/components/responses/400BadRequest
        '401':
          $ref: common.yaml#/components/responses/401Unauthorized
        '403':
          $ref: common.yaml#/components/responses/403Forbidden
        '404':
          $ref: common.yaml#/components/responses/404NotFound
        '405':
          $ref: common.yaml#/components/responses/405MethodNotAllowed
        '500':
          $ref: common.yaml#/components/responses/500InternalServerError
        '503':
          $ref: common.yaml#/components/responses/503ServiceUnavailable
        '504':
          $ref: common.yaml#/components/responses/504GatewayTimeout
components:
  schemas:
    EmbedResponse:
      type: object
      properties:
        object:
          type: string
          description: Type of the response object
          enum:
          - list
        data:
          type: array
          description: List of embedding objects
          items:
            type: object
            properties:
              object:
                type: string
                description: Type of the embedding object
                enum:
                - embedding
              embedding:
                type: array
                description: Nested array of floating-point numbers representing the embedding vector
                items:
                  type: array
                  items:
                    type: number
                    format: float
              index:
                type: integer
                description: Index of the embedding in the input array
            required:
            - object
            - embedding
            - index
        model:
          type: string
          description: Name of the embedding model used
        usage:
          type: object
          properties:
            total_tokens:
              type: integer
              description: Total number of tokens processed
      required:
      - object
      - data
      - model
      - usage
    EmbedRequest:
      type: object
      description: Request to calculate text embeddings using a specified model.
      properties:
        model:
          type: string
          description: "Identifier of the model to use for generating embeddings.\nRefer to Snowflake documentation for the list of supported models.\n\nExamples:\n  - `snowflake-arctic-embed-m`\n  - `snowflake-arctic-embed-m-v1.5`\n"
        text:
          type: array
          items:
            type: string
          description: 'An array of input texts for which vector embeddings will be calculated.

            Example: ["Hello world", "Machine learning is fascinating"]'
          minItems: 1
        provisioned_throughput_id:
          type:
          - string
          - 'null'
          description: The provisioned throughput ID to be used with the request.
      required:
      - model
      - text
  securitySchemes:
    KeyPair:
      $ref: common.yaml#/components/securitySchemes/KeyPair
    ExternalOAuth:
      $ref: common.yaml#/components/securitySchemes/ExternalOAuth
    SnowflakeOAuth:
      $ref: common.yaml#/components/securitySchemes/SnowflakeOAuth
    ProgrammaticAccessToken:
      $ref: common.yaml#/components/securitySchemes/ProgrammaticAccessToken

Cortex Embed API

Operations 1

Documentation

Specifications

Schemas & Data

Other Resources