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

# Gemini Native Format

> Gemini-compatible generateContent and streaming endpoints

The native Gemini routes are implemented for compatible models. The current GPT 5.6, Kimi K3, and Claude 5 model set does not support this protocol; using one of those model IDs returns a Gemini-formatted unsupported-model error.

For streaming, call `POST /v1beta/models/{model}:streamGenerateContent` and consume the SSE response.


## OpenAPI

````yaml POST /v1beta/models/{model}:generateContent
openapi: 3.1.0
info:
  title: Vidgo Gemini Native
  version: 1.0.0
servers:
  - url: https://api.vidgo.ai
security: []
paths:
  /v1beta/models/{model}:generateContent:
    post:
      summary: Generate Gemini content
      parameters:
        - name: model
          in: path
          required: true
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              additionalProperties: true
      responses:
        '200':
          description: Gemini response
        '400':
          description: Unsupported model or protocol
      security:
        - bearerAuth: []
        - googleApiKey: []
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
    googleApiKey:
      type: apiKey
      in: header
      name: x-goog-api-key

````