Send a prompt to Gemini and get a text response. Optionally enable search grounding or URL context.

Analyze an image file with Gemini Vision

Analyze an audio file with Gemini (transcribe, summarize, describe)

Analyze a video file with Gemini (describe, summarize, extract info)

Analyze a PDF document with Gemini (summarize, extract, answer questions)

Multi-turn conversation with Gemini using message history

Send a prompt to Gemini with Google Search grounding and URL context for up-to-date information

Get structured JSON output from Gemini using a provided JSON schema

Analyze one or more URLs using Gemini URL context tool. Gemini fetches and reads the URLs directly.

Flexible Gemini chat with mode switching: "search" (Google Search + URL context), "code" (code execution), or "all" (everything)

Start a deep research task using Gemini Deep Research. Returns an interaction ID. Then call gemini_check_research with wait=true in the background to get notified when complete.

Check or wait for deep research results. Use wait=true to block until completion (ideal for background execution — the tool returns when research finishes, triggering a task notification in your AI client).

Upload a file to Gemini Files API for use with analysis tools. Files are retained for 48 hours. Max 2GB per file, 20GB total.

List files uploaded to the Gemini Files API

Delete a file from the Gemini Files API

Analyze a public YouTube video with Gemini (summarize, transcribe, answer questions). Supports up to 10 videos with Gemini 2.5+ models.

Analyze a file from a public URL (HTTP/HTTPS) or Google Cloud Storage URI (gs://). Supports images, audio, video, PDFs, and documents up to 100MB.

List available Gemini models with their capabilities and token limits

Count the number of tokens in the provided text using a Gemini model

Generate text embeddings using a Gemini embedding model

Generate and execute code using Gemini's built-in code execution capability

Summarize long text using Gemini with configurable summary style

Translate text to a target language using Gemini