> ## 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

Use a model that supports the Gemini native protocol. Unsupported model IDs return a Gemini-formatted error response.

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

## Additional supported models

* `google/gemini-3.7-flash`
* `google/gemini-3.5-flash`

Use the complete public ID in the URL, including the provider slash. For example: `/v1beta/models/google/gemini-3.7-flash:generateContent`. Send a non-empty contents array. Streaming uses `:streamGenerateContent?alt=sse`.


## 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
      description: >-
        Uses the native protocol request body, without a generation input
        wrapper. JSON and SSE response bodies are forwarded from the upstream;
        returned model names may differ from the Vidgo public ID. Authentication
        errors may use a detail field; protocol errors use the protocol error
        shape.
      parameters:
        - name: model
          in: path
          required: true
          schema:
            type: string
            enum:
              - google/gemini-3.7-flash
              - google/gemini-3.5-flash
          description: Complete Vidgo public model ID, including the provider slash.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              additionalProperties: true
              properties:
                contents:
                  type: array
                  minItems: 1
                  items:
                    type: object
                    additionalProperties: true
              required:
                - contents
            examples:
              workflow:
                summary: Vidgo workflow example
                value:
                  contents:
                    - role: user
                      parts:
                        - text: Hello
      responses:
        '200':
          description: Gemini response
          content:
            application/json:
              schema:
                type: object
                additionalProperties: true
        '400':
          description: Unsupported model or protocol
        '401':
          description: Invalid credentials
        '402':
          description: Insufficient credits
        '403':
          description: Access denied
        '404':
          description: Vendor context not found
        '408':
          description: Request timed out
          content:
            text/plain:
              schema:
                type: string
              example: Request timeout
        '422':
          description: Invalid JSON or non-object request body
        '429':
          description: Upstream rate limit exceeded
        '502':
          description: Upstream connection or response error
      security:
        - bearerAuth: []
        - googleApiKey: []
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
    googleApiKey:
      type: apiKey
      in: header
      name: x-goog-api-key

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.