Skip to main content
POST
Generate content (Gemini)
This page uses the same generateContent operation as Generate content (Gemini), with the playground above pre-filled for plain text chat. The notes below describe the Gemini-native fields you can add to generationConfig to generate or edit images with provider-specific response controls.
Set generationConfig.responseModalities to ["IMAGE"] to request image output, and use generationConfig.imageConfig to control the aspect ratio and output size.

Gemini-native request fields

Use an image-generation-capable model such as gemini-2.0-flash-preview-image-generation in the model path parameter.

Example: generating an image

Response fields

The response follows the standard generateContent shape. When image output is requested, the returned parts contain inline image data:
array
Candidate responses returned by the model.
object
Token usage metadata, including promptTokenCount, candidatesTokenCount, and totalTokenCount.

Example response

200

Authorizations

Authorization
string
header
required

Your DGrid API key. All endpoints use Authorization: Bearer <DGRID_API_KEY>.

Path Parameters

model
string
required

Target model ID, such as gemini-1.5-pro.

Body

application/json
contents
object[]

Input content array with role and parts.

generationConfig
object

Generation configuration.

Response

Generated content candidates.

candidates
object[]

Candidate responses returned by the model.

usageMetadata
object

Token accounting metadata.