Gemini API Gateway for Openclaw

A high-performance gateway providing direct access to Google Gemini models with 1 million token context windows without requiring a Google Cloud account.

xiaoyinqu
v1.0.0
Mar 4, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install gemini-api

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install gemini-api using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Gemini API Gateway?

The Gemini API skill offers a robust bridge between the Openclaw Skills framework and Google's most advanced generative models, including Gemini 3 Pro and Gemini 2.5 Flash. This integration allows developers to process massive datasets, entire codebases, or long-form video content within their AI agent workflows. By leveraging the SkillBoss backend, users benefit from an OpenAI-compatible interface that simplifies migration and multi-model orchestration.

This skill is designed for high-throughput environments where speed and cost-efficiency are paramount. Whether you are using Gemini 2.5 Flash for rapid responses or Gemini 3 Pro for complex reasoning, this gateway ensures seamless connectivity. It eliminates the administrative overhead of managing Google Cloud projects while providing zero-markup pricing on token usage.

Gemini API Gateway Use Cases

  • Analyzing entire repositories or long documents using the massive 1 million token context window.
  • Building low-latency chat applications using the Gemini 2.5 Flash Lite model for minimal costs.
  • Performing multi-modal analysis including video and image processing directly through the agent.
  • Creating resilient AI systems that can failover to alternative providers if primary models are unavailable.

How Gemini API Gateway Works

  1. The agent initializes the connection using the provided SkillBoss API key.
  2. Users specify the desired model variant, such as Gemini 2.5 Pro or Flash, via standard command prefixes.
  3. The skill formats the request into an OpenAI-compatible payload and transmits it to the high-speed gateway.
  4. The response is streamed back to the agent, allowing for real-time processing of large-scale context.

Gemini API Gateway Setup

To integrate this capability into your Openclaw Skills environment, follow these steps:

  1. Obtain your API key from the SkillBoss console.
  2. Install the setup script:
curl -fsSL https://skillboss.co/openclaw-setup.sh | bash
  1. Export your API key as an environment variable:
export SKILLBOSS_API_KEY='your_api_key_here'
  1. Select your model and begin prompting.

Gemini API Gateway Data Schema & Taxonomy

The skill utilizes the following model configurations and metadata for request routing:

Model Variant Context Window Best Use Case
gemini-3-pro 1,000,000 tokens Complex reasoning and large codebase analysis
gemini-2.5-pro 1,000,000 tokens High-accuracy tasks requiring long memory
gemini-2.5-flash 1,000,000 tokens High-speed production workloads
gemini-2.5-flash-lite 1,000,000 tokens Ultra-low cost, high-volume processing

Gemini API Gateway Advanced Features

  • Multi-model failover support ensures your Openclaw Skills continue functioning by automatically switching to Claude or GPT models if Gemini is unreachable.
  • Zero-markup pricing architecture ensures you pay the direct provider rates for all token consumption.
  • Native multi-modal support allows for the analysis of video files and complex imagery within a single context window.
  • OpenAI-compatible API schema allows for drop-in replacement in existing AI development pipelines.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*