OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI APIs & Platforms

Genai API

Genai API is an open-source TypeScript API built with Hono that connects applications to Gemini through a Cloudflare Worker. Its completion endpoint accepts text or text with an image data URL and returns a plain-text model completion.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Genai API — OpenViST project profile in AI APIs & Platforms.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a self-managed Cloudflare Worker endpoint between a client application or Apple Shortcut and Gemini, and can configure the required provider key and bearer token.

Who it is for

  • Developers adding Gemini responses to applications running through a Cloudflare Worker.
  • Apple Shortcuts makers who want to call a Gemini-backed API from a shortcut.

Documented uses

  • Send text prompts to Gemini and receive a plain-text completion.
  • Submit text with an image data URL for tasks such as visual question answering or image captioning.
  • Provide an authenticated backend interface between an application or shortcut and Google AI Studio's listed Gemini models.
Before you choose

Requirements & limits

The repository is public and declares an Apache-2.0 license. Deployment requires a Google AI Studio API key and a bearer token.

  • The documented provider is google-ai-studio; listed models are gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.0-flash and gemini-2.0-flash-lite.
  • Image input must be provided as a valid data URL.
  • Every request needs an Authorization bearer token; an X-API-Key header can be used for a provider-specific key.
  • The documented response is plain text, even when the request includes an image.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Deploy the API to Cloudflare Workers

Configure the repository's API credentials and deploy the Worker.

Before you start

  • The Genai API repository and Wrangler setup.
  • A Google AI Studio API key.
  • A Cloudflare Worker configuration, including edits to wrangler.jsonc where needed.
  • A bearer token.

Steps

  1. Download the repository and edit the configuration files, including wrangler.jsonc as needed.

  2. Run make init; run make update if needed.

  3. Use Wrangler to store GOOGLE_AI_STUDIO_API_KEY and BEARER_TOKEN as secrets.

  4. Run make deploy to deploy the API to Cloudflare Workers.

Expected outcome

A deployed Worker with the documented /api/v1/completion route available for requests.

Guide limitations

  • Requests to the completion endpoint require an Authorization bearer token.
  • The guide does not specify endpoint behavior beyond the documented completion request format.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
louisbrulenaudet/genai-api · Official homepage title · retained in its source language
How we review sourcesSuggest a correction