AI

Gemini

Gemini is Google's model family served by the Gemini API — text and multimodal generation, embeddings, Imagen images, Veo video, and a short-lived file store the models can read from.

Actions

Generic API request. Call any Gemini API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Delete FileDestructiveDelete one uploaded file before its automatic 48-hour expiry (DELETE /v1beta/files/{name}).
  • Download VideoDownload a Veo-generated video from the URI a finished operation reports (GET on that URI).
  • EmbeddingsGemini embeddings via connection context and HTTP POST /models/{model}:batchEmbedContents.
  • Generate ContentGemini generateContent via connection context and HTTP POST.
  • Generate Content (Streaming)Streaming Gemini generateContent.
  • Generate VideoSubmit a Veo video generation job (POST /models/{model}:predictLongRunning).
  • Get FileRetrieve one uploaded file's metadata by resource name, including the state that says whether it is ready to reference (GET /v1beta/files/{name}).
  • Get OperationCheck a long-running Gemini operation (GET /{operationname}).
  • List FilesList the files uploaded on the connection's Gemini account, one page at a time (GET /v1beta/files).
  • List modelsLists Gemini models via connection context and HTTP GET /models.
  • Text to speechGenerate single- or two-speaker audio with a Gemini TTS model.
  • Upload FileUpload a file to the Gemini Files API and get back a files/...

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.