gemini-openai-api

Access Gemini models through OpenAI-compatible endpoints with JSON-wrapped response handling.

2.4k|275|Updated Jun 29, 2025
One-click install
npx skills add https://github.com/Project-N-E-K-O/N.E.K.O --skill gemini-openai-api
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-openai-api
Source: https://github.com/Project-N-E-K-O/N.E.K.O/tree/main/.agent/skills/gemini-openai-api
Command: npx skills add https://github.com/Project-N-E-K-O/N.E.K.O --skill gemini-openai-api

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gemini models can be accessed via OpenAI-compatible endpoints, enable seamless integration into existing AI workflows.

Core Features & Use Cases

  • OpenAI-compatible endpoint access for Gemini models.
  • Model configuration support (summary/correction/emotion/vision) with recommended model mappings.
  • Thinking control via extra_body and robust response handling for JSON-wrapped outputs across use cases such as assistants, copilots, and chatbots.

Quick Start

Point your client at the Gemini OpenAI-compatible endpoint and configure the model names as described below, then send a simple prompt to verify integration.

Frequently Asked Questions about gemini-openai-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I access Gemini models through OpenAI-compatible endpoints?

Access Gemini models through OpenAI-compatible endpoints by configuring provider mappings, model-name mappings, and client-side request parsing to integrate seamlessly into existing AI workflows.

What is the best way to control Gemini thinking in an OpenAI API workflow?

Control Gemini thinking in an OpenAI API workflow by using the extra_body parameter in your client requests, enabling you to toggle and configure the model's reasoning capabilities.

How do I handle JSON-wrapped responses from Gemini via OpenAI API endpoints?

Handle JSON-wrapped responses from Gemini via OpenAI API endpoints by implementing client-side response parsing to extract outputs for assistants, copilots, and chatbots.

Which Gemini model configurations are supported for OpenAI API integration?

Supported Gemini model configurations for OpenAI API integration include summary, correction, emotion, and vision, each utilizing recommended model-name mappings for specific use cases.

Do I need to configure provider mappings to use Gemini with OpenAI API clients?

Yes, configuring provider mappings via an api_providers.json file is required to operate the Gemini OpenAI-compatible interface and route requests correctly from your existing clients.

Why does my OpenAI client fail to parse Gemini responses for chatbot use cases?

OpenAI client parsing failures for Gemini chatbot responses often occur when client-side request and response parsing lacks the proper handling for Gemini's JSON-wrapped outputs.