Eden AI Prompt Optimization API

openapi: 3.2.0
info:
  title: Text Features Prompt Optimization API
  version: '2.0'
  description: Your project description
servers:
- url: https://api.edenai.run/v2
tags:
- name: Prompt Optimization
paths:
  /text/prompt_optimization/:
    post:
      operationId: text_prompt_optimization_create
      description: 'Available Providers


        |Provider|Model|Version|Price|Billing unit|

        |----|----|-------|-----|------------|

        |**openai**|**gpt-4**|`v3.0.0`|6e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4-turbo**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo**|`v3.0.0`|1.5e-06 (per 1 token)|1 token

        |**openai**|**chatgpt-4o-latest**|`v3.0.0`|1.5e-05 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-0125**|`v3.0.0`|1.5e-06 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-0301**|`v3.0.0`|2e-06 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-0613**|`v3.0.0`|2e-06 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-1106**|`v3.0.0`|2e-06 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-16k**|`v3.0.0`|4e-06 (per 1 token)|1 token

        |**openai**|**gpt-3.5-turbo-16k-0613**|`v3.0.0`|4e-06 (per 1 token)|1 token

        |**openai**|**gpt-4-0125-preview**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-0314**|`v3.0.0`|6e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-0613**|`v3.0.0`|6e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-1106-preview**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-1106-vision-preview**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-32k**|`v3.0.0`|0.00012 (per 1 token)|1 token

        |**openai**|**gpt-4-32k-0314**|`v3.0.0`|0.00012 (per 1 token)|1 token

        |**openai**|**gpt-4-32k-0613**|`v3.0.0`|0.00012 (per 1 token)|1 token

        |**openai**|**gpt-4-turbo-2024-04-09**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-turbo-preview**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4-vision-preview**|`v3.0.0`|3e-05 (per 1 token)|1 token

        |**openai**|**gpt-4.1**|`v3.0.0`|8e-06 (per 1 token)|1 token

        |**openai**|**gpt-4.1-2025-04-14**|`v3.0.0`|8e-06 (per 1 token)|1 token

        |**openai**|**gpt-4.1-mini**|`v3.0.0`|1.6e-06 (per 1 token)|1 token

        |**openai**|**gpt-4.1-mini-2025-04-14**|`v3.0.0`|1.6e-06 (per 1 token)|1 token

        |**openai**|**gpt-4.1-nano**|`v3.0.0`|4e-07 (per 1 token)|1 token

        |**openai**|**gpt-4.1-nano-2025-04-14**|`v3.0.0`|4e-07 (per 1 token)|1 token

        |**openai**|**gpt-4.5-preview**|`v3.0.0`|0.00015 (per 1 token)|1 token

        |**openai**|**gpt-4.5-preview-2025-02-27**|`v3.0.0`|0.00015 (per 1 token)|1 token

        |**openai**|**gpt-4o-2024-05-13**|`v3.0.0`|1.5e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-2024-08-06**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-2024-11-20**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-audio-preview**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-audio-preview-2024-10-01**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-audio-preview-2024-12-17**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-audio-preview-2025-06-03**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-2024-07-18**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-audio-preview**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-audio-preview-2024-12-17**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-realtime-preview**|`v3.0.0`|2.4e-06 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-realtime-preview-2024-12-17**|`v3.0.0`|2.4e-06 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-search-preview**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4o-mini-search-preview-2025-03-11**|`v3.0.0`|6e-07 (per 1 token)|1 token

        |**openai**|**gpt-4o-realtime-preview**|`v3.0.0`|2e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-realtime-preview-2024-10-01**|`v3.0.0`|2e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-realtime-preview-2024-12-17**|`v3.0.0`|2e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-realtime-preview-2025-06-03**|`v3.0.0`|2e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-search-preview**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-4o-search-preview-2025-03-11**|`v3.0.0`|1e-05 (per 1 token)|1 token

        |**openai**|**gpt-5**|`v3.0.0`|1e-05 (per 1 token)|1…'
      summary: Prompt Optimization
      tags:
      - Prompt Optimization
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/textprompt_optimizationPromptOptimizationRequest'
            examples:
              RequestExample:
                value:
                  providers: openai
                  text: Entity extractor, i give you an entity or multiple entities and a text and i want the entitites extracted from the text
                  target_provider: google
                summary: Request Example
        required: true
      security:
      - FeatureApiAuth: []
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/textprompt_optimizationResponseModel'
              examples:
                ResponseExample:
                  value:
                    openai:
                      missing_information: What type of entities are you specifically looking to extract (names, locations, organizations, etc.)? Do you have any specific language or data format preferences for the text? Do you need this tool to handle any particular size, complexity, or other special characteristics of the texts?
                      items:
                      - text: Given the following text and a list of entities, please extract and list all occurrences of the specified entities in the text. The entities to be extracted are [entities]. The text for entity extraction is [text].
                      - text: 'Given the following text, please identify and extract all instances of the specified entities. The entities to look for are [Entity1, Entity2, Entity3]. Here is the text: [Insert Text Here]. Please list the extracted entities in a clear and organized manner.'
                      - text: 'Given the following text and a list of entities, please extract and list all instances of the provided entities within the text. The entities are [list of entities]. The text is as follows: [text]. Please format your response as a bulleted list, with each bullet representing an instance of an entity found in the text.'
                      cost: 0.0
                  summary: Response Example
          description: ''
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BadRequest'
          description: ''
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
          description: ''
        '403':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
          description: ''
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundResponse'
          description: ''
components:
  schemas:
    BadRequest:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedBadRequest'
      required:
      - error
    textprompt_optimizationPromptOptimizationRequest:
      type: object
      properties:
        settings:
          type: string
          default: {}
          description: "A dictionnary or a json object to specify specific models to use for some providers. <br>                     It can be in the following format: {\"google\" : \"google_model\", \"ibm\": \"ibm_model\"...}.\n                     "
        providers:
          type: array
          items:
            type: string
            minLength: 1
          description: 'It can be one (ex: **''amazon''** or **''google''**) or multiple provider(s) (ex: **''amazon,microsoft,google''**)             that the data will be redirected to in order to get the processed results.<br>             Providers can also be invoked with specific models (ex: providers: **''amazon/model1, amazon/model2, google/model3''**)'
        fallback_providers:
          type: array
          items:
            type: string
          default: []
          description: "Providers in this list will be used as fallback if the call to provider in `providers` parameter fails.\n    To use this feature, you must input **only one** provider in the `providers` parameter. but you can put up to 5 fallbacks.\n\nThey will be tried in the same order they are input, and it will stop to the first provider who doesn't fail.\n\n\n*Doesn't work with async subfeatures.*\n    "
          maxItems: 5
        response_as_dict:
          type: boolean
          default: true
          description: "Optional : When set to **true** (default), the response is an object of responses with providers names as keys : <br> \n                  ``` {\"google\" : { \"status\": \"success\", ... }, } ``` <br>\n                When set to **false** the response structure is a list of response objects : <br> \n                   ``` [{\"status\": \"success\", \"provider\": \"google\" ... }, ] ```. <br>\n                  "
        attributes_as_list:
          type: boolean
          default: false
          description: "Optional : When set to **false** (default) the structure of the extracted items is list of objects having different attributes : <br>\n     ```{'items': [{\"attribute_1\": \"x1\",\"attribute_2\": \"y2\"}, ... ]}``` <br>\n     When it is set to **true**, the response contains an object with each attribute as a list : <br>\n     ```{ \"attribute_1\": [\"x1\",\"x2\", ...], \"attribute_2\": [y1, y2, ...]}``` "
        show_base_64:
          type: boolean
          default: true
        show_original_response:
          type: boolean
          default: false
          description: "Optional : Shows the original response of the provider.<br>\n        When set to **true**, a new attribute *original_response* will appear in the response object."
        text:
          type: string
          minLength: 1
          description: Description of the desired prompt.
        target_provider:
          type: string
          minLength: 1
          description: Select the provider for the prompt optimization
      required:
      - providers
      - target_provider
      - text
    NotFoundResponse:
      type: object
      properties:
        details:
          type: string
          default: Not Found
    textprompt_optimizationPromptOptimizationDataClass:
      properties:
        missing_information:
          title: Missing Information
          type: string
        items:
          items:
            $ref: '#/components/schemas/PromptDataClass'
          title: Items
          type: array
        original_response:
          default: null
          description: original response sent by the provider, hidden by default, show it by passing the `show_original_response` field to `true` in your request
          title: Original Response
        status:
          allOf:
          - $ref: '#/components/schemas/StatusEnum'
          title: Status
      required:
      - missing_information
      - status
      title: textprompt_optimizationPromptOptimizationDataClass
      type: object
    FieldError:
      type: object
      properties:
        <parameter_name>:
          type: array
          items:
            type: string
      required:
      - <parameter_name>
    PromptDataClass:
      properties:
        text:
          title: Text
          type: string
      required:
      - text
      title: PromptDataClass
      type: object
    Error:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/NestedError'
      required:
      - error
    StatusEnum:
      enum:
      - sucess
      - fail
      type: string
    NestedBadRequest:
      type: object
      properties:
        type:
          type: string
        message:
          $ref: '#/components/schemas/FieldError'
      required:
      - message
      - type
    NestedError:
      type: object
      properties:
        type:
          type: string
        message:
          type: string
      required:
      - message
      - type
    textprompt_optimizationResponseModel:
      properties:
        openai:
          $ref: '#/components/schemas/textprompt_optimizationPromptOptimizationDataClass'
          default: null
      title: textprompt_optimizationResponseModel
      type: object
  securitySchemes:
    FeatureApiAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT