API

Every gemini.api.* operation is listed below with parameter shapes and return types from the plugin Zod schemas.

New to Corsair? See API access, authentication, and error handling.

Content

countTokens

content.countTokens Count tokens in text using Gemini tokenization, for cost estimation and input limit checks Risk: read

await corsair.gemini.api.content.countTokens({});

Input

Name	Type	Required	Description
`model`	`string`	Yes	Gemini model to count tokens against, e.g. gemini-2.5-flash, gemini-2.5-pro
`contents`	`object[]`	Yes	The content to count tokens for

contents full type

{
  role?: user | model,
  parts: {
    text?: string,
    inlineData?: {
      mimeType: string,
      data: string
    }
  }[]
}[]

Output

Name	Type	Required	Description
`totalTokens`	`number`	Yes	—
`cachedContentTokenCount`	`number`	No	—

embedContent

content.embedContent Generate a numerical vector embedding for text, for semantic search and similarity comparison Risk: read

await corsair.gemini.api.content.embedContent({});

Input

Name	Type	Required	Description
`model`	`string`	Yes	Gemini embedding model, e.g. gemini-embedding-001
`content`	`object`	Yes	The content to embed
`taskType`	`string`	No	Optional task type hint, e.g. SEMANTIC_SIMILARITY, RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, CLASSIFICATION, CLUSTERING
`title`	`string`	No	Optional title, used with RETRIEVAL_DOCUMENT taskType

content full type

{
  role?: user | model,
  parts: {
    text?: string,
    inlineData?: {
      mimeType: string,
      data: string
    }
  }[]
}

Output

Name	Type	Required	Description
`embedding`	`object`	Yes	—

embedding full type

{
  values: number[]
}

generateContent

content.generateContent Generate text or speech audio from a prompt using a Gemini Flash/Pro model Risk: read

await corsair.gemini.api.content.generateContent({});

Input

Name	Type	Required	Description
`model`	`string`	Yes	Gemini model to generate with, e.g. gemini-2.5-flash, gemini-2.5-pro
`contents`	`object[]`	Yes	Conversation contents to generate a response for
`generationConfig`	`object`	No	—
`safetySettings`	`object[]`	No	—
`systemInstruction`	`object`	No	—

contents full type

{
  role?: user | model,
  parts: {
    text?: string,
    inlineData?: {
      mimeType: string,
      data: string
    }
  }[]
}[]

generationConfig full type

{
  temperature?: number,
  topP?: number,
  topK?: number,
  candidateCount?: number,
  maxOutputTokens?: number,
  stopSequences?: string[],
  responseModalities?: TEXT | IMAGE | AUDIO[]
}

safetySettings full type

{
  category: string,
  threshold: string
}[]

systemInstruction full type

{
  role?: user | model,
  parts: {
    text?: string,
    inlineData?: {
      mimeType: string,
      data: string
    }
  }[]
}

Output

Name	Type	Required	Description
`candidates`	`object[]`	No	—
`usageMetadata`	`object`	No	—
`text`	`string`	No	Convenience field: first candidate text with markdown code fences stripped

candidates full type

{
  content?: {
    role?: user | model,
    parts: {
      text?: string,
      inlineData?: {
        mimeType: string,
        data: string
      }
    }[]
  },
  finishReason?: string,
  index?: number,
  safetyRatings?: any[]
}[]

usageMetadata full type

{
  promptTokenCount?: number,
  candidatesTokenCount?: number,
  totalTokenCount?: number,
  cachedContentTokenCount?: number
}

Images

generateImage

images.generateImage Generate a raster image (JPG/PNG/WebP) from a prompt using a Nano Banana image model Risk: write

await corsair.gemini.api.images.generateImage({});

Input

Name	Type	Required	Description
`model`	`string`	Yes	Nano Banana image model, e.g. gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-2.0-flash-exp-image-generation
`prompt`	`string`	Yes	Text prompt describing the image to generate
`referenceImages`	`object[]`	No	Optional reference/input images for image editing or composition
`generationConfig`	`object`	No	—

referenceImages full type

{
  mimeType: string,
  data: string
}[]

generationConfig full type

{
  temperature?: number,
  topP?: number,
  topK?: number,
  candidateCount?: number,
  maxOutputTokens?: number,
  stopSequences?: string[],
  responseModalities?: TEXT | IMAGE | AUDIO[]
}

Output

Name	Type	Required	Description
`images`	`object[]`	Yes	—
`candidates`	`object[]`	No	—
`usageMetadata`	`object`	No	—

images full type

{
  mimeType: string,
  contentBase64: string
}[]

candidates full type

{
  content?: {
    role?: user | model,
    parts: {
      text?: string,
      inlineData?: {
        mimeType: string,
        data: string
      }
    }[]
  },
  finishReason?: string,
  index?: number,
  safetyRatings?: any[]
}[]

usageMetadata full type

{
  promptTokenCount?: number,
  candidatesTokenCount?: number,
  totalTokenCount?: number,
  cachedContentTokenCount?: number
}

Models

listModels

models.listModels List available Gemini and Veo models and their capabilities/limits Risk: read

await corsair.gemini.api.models.listModels({});

Input

Name	Type	Required	Description
`pageSize`	`number`	No	—
`pageToken`	`string`	No	—

Output

Name	Type	Required	Description
`models`	`object[]`	Yes	—
`nextPageToken`	`string`	No	—

models full type

{
  name: string,
  baseModelId?: string,
  version?: string,
  displayName?: string,
  description?: string,
  inputTokenLimit?: number,
  outputTokenLimit?: number,
  supportedGenerationMethods?: string[],
  temperature?: number,
  topP?: number,
  topK?: number
}[]

Videos

generateVideos

videos.generateVideos Generate a text-to-video clip using a Veo model; returns an operation name for status tracking Risk: write

await corsair.gemini.api.videos.generateVideos({});

Input

Name	Type	Required	Description
`model`	`string`	Yes	Veo video model, e.g. veo-2.0-generate-001
`prompt`	`string`	Yes	Text prompt describing the video to generate
`image`	`object`	No	—
`parameters`	`object`	No	—

image full type

{
  bytesBase64Encoded: string,
  mimeType: string
}

parameters full type

{
  aspectRatio?: string,
  personGeneration?: string,
  numberOfVideos?: number,
  durationSeconds?: number,
  negativePrompt?: string
}

Output

Name	Type	Required	Description
`operationName`	`string`	Yes	Pass to GEMINI_GET_VIDEOS_OPERATION or GEMINI_WAIT_FOR_VIDEO
`done`	`boolean`	No	—

getVideosOperation

videos.getVideosOperation (Deprecated — use videos.waitForVideo) Check the status of a Veo video generation operation Risk: read

await corsair.gemini.api.videos.getVideosOperation({});

Input

Name	Type	Required	Description
`operationName`	`string`	Yes	The operation name returned by GEMINI_GENERATE_VIDEOS

Output

Name	Type	Required	Description
`name`	`string`	Yes	—
`done`	`boolean`	No	—
`metadata`	`any`	No	—
`error`	`object`	No	—
`response`	`object`	No	—

error full type

{
  code?: number,
  message?: string
}

response full type

{
  generateVideoResponse?: {
    generatedSamples?: {
      video?: {
        uri?: string
      }
    }[]
  }
}

waitForVideo

videos.waitForVideo Poll a Veo video generation operation until it completes and return the generated video Risk: write

await corsair.gemini.api.videos.waitForVideo({});

Input

Name	Type	Required	Description
`operationName`	`string`	Yes	The operation name returned by GEMINI_GENERATE_VIDEOS
`pollIntervalMs`	`number`	Yes	Delay between status checks
`timeoutMs`	`number`	Yes	Give up and return done=false after this long

Output

Name	Type	Required	Description
`operationName`	`string`	Yes	—
`done`	`boolean`	Yes	—
`data`	`object`	No	—
`error`	`object`	No	—

data full type

{
  video_file?: {
    mimeType: string,
    contentBase64: string
  }
}

error full type

{
  code?: number,
  message?: string
}

Overview

Plugins

Content

countTokens

embedContent

generateContent

Images

generateImage

Models

listModels

Videos

generateVideos

getVideosOperation

waitForVideo

​Content

​countTokens

​embedContent

​generateContent

​Images

​generateImage

​Models

​listModels

​Videos

​generateVideos

​getVideosOperation

​waitForVideo

Content

countTokens

embedContent

generateContent

Images

generateImage

Models

listModels

Videos

generateVideos

getVideosOperation

waitForVideo