> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# EvoLink Auto - Gemini 형식

> Intelligent routing using Google Generative AI format

## 스마트 모델 라우팅

Google Generative AI 형식을 사용하여 EvoLink Auto 지능형 모델 라우팅을 호출합니다.

### 주요 특징

* **Gemini 네이티브 형식**: Google Generative AI API와 완벽하게 호환
* **지능형 라우팅**: 적합한 모델을 자동으로 선택
* **투명한 응답**: 실제 사용된 모델 버전을 포함

<Note>
  경로 매개변수에 `evolink/auto`를 사용하고 `/v1beta/models/evolink/auto:generateContent` 엔드포인트를 호출하세요.
</Note>

<Note>
  **BaseURL**: 기본 BaseURL은 `https://direct.evolink.ai`이며, 텍스트 모델 지원이 더 우수하고 장시간 연결을 지원합니다. `https://api.evolink.ai`는 멀티모달 서비스의 주력 엔드포인트이며, 텍스트 모델에 대해서는 대체 주소로 사용됩니다.
</Note>


## OpenAPI

````yaml ko/api-manual/language-series/evolink-auto/evolink-auto-gemini.json POST /v1beta/models/{model}:generateContent
openapi: 3.1.0
info:
  title: EvoLink Auto - Gemini Format
  description: Intelligent model routing using Google Generative AI format
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://direct.evolink.ai
    description: Standard API
security:
  - bearerAuth: []
paths:
  /v1beta/models/{model}:generateContent:
    post:
      tags:
        - Intelligent Routing
      summary: Intelligent Model Routing (Gemini Format)
      description: Intelligent routing using Google Generative AI format
      operationId: generateContentAuto
      parameters:
        - name: model
          in: path
          required: true
          schema:
            type: string
            enum:
              - evolink/auto
            example: evolink/auto
          description: Model name, use evolink/auto to enable intelligent routing
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GeminiAutoRequest'
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GeminiResponse'
components:
  schemas:
    GeminiAutoRequest:
      type: object
      required:
        - contents
      properties:
        contents:
          type: array
          description: Conversation content list
          items:
            type: object
            properties:
              role:
                type: string
                enum:
                  - user
                  - model
              parts:
                type: array
                items:
                  type: object
                  properties:
                    text:
                      type: string
          example:
            - role: user
              parts:
                - text: Introduce the history of artificial intelligence
        generationConfig:
          type: object
          properties:
            temperature:
              type: number
              minimum: 0
              maximum: 2
              example: 0.7
            topP:
              type: number
              minimum: 0
              maximum: 1
              example: 0.9
            topK:
              type: integer
              minimum: 1
              example: 40
            maxOutputTokens:
              type: integer
              example: 1024
    GeminiResponse:
      type: object
      properties:
        candidates:
          type: array
          items:
            type: object
            properties:
              content:
                type: object
                properties:
                  parts:
                    type: array
                    items:
                      type: object
                      properties:
                        text:
                          type: string
                  role:
                    type: string
                    enum:
                      - model
              finishReason:
                type: string
        usageMetadata:
          type: object
          properties:
            promptTokenCount:
              type: integer
            candidatesTokenCount:
              type: integer
            totalTokenCount:
              type: integer
        modelVersion:
          type: string
          description: Actual model version used
          example: gemini-2.5-pro
      example:
        candidates:
          - content:
              parts:
                - text: 인공지능의 발전 역사는 1950년대로 거슬러 올라갑니다...
              role: model
            finishReason: STOP
        usageMetadata:
          promptTokenCount: 15
          candidatesTokenCount: 156
          totalTokenCount: 171
        modelVersion: gpt-5.4
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        ##All APIs require Bearer Token authentication##


        **Get API Key:**


        Visit [API Key Management](https://evolink.ai/dashboard/keys) to get
        your API Key


        **Add to request header:**

        ```

        Authorization: Bearer YOUR_API_KEY

        ```
      bearerFormat: sk-evo-xxxxxxxxxx

````