How to Use Google Gemini with OpenClaw?

Google Gemini models work with OpenClaw through the Google AI Studio API. Gemini 2.5 Pro is competitive with Claude and GPT-4o, with the bonus of a massive 1M token context window.

Get your API key from aistudio.google.com. Google offers a generous free tier — 15 requests per minute and 1 million tokens per day for Gemini 2.5 Flash, making it one of the cheapest options for moderate usage.

Gemini 2.5 Pro ($1.25/1M input, $10/1M output) is excellent for long document analysis thanks to its huge context window. Gemini 2.5 Flash ($0.15/1M input, $0.60/1M output) is the budget choice — extremely cheap with decent quality.

OpenClaw connects to Gemini via the OpenAI-compatible API endpoint that Google provides. Configuration is straightforward — set the provider, model, and API key.

Gemini excels at: multimodal tasks (text + images), long document processing, structured data extraction, and multilingual content. It supports function calling, which integrates well with OpenClaw's MCP skills.

Tip: Try Gemini Flash for a nearly-free AI agent experience. If you need higher quality, upgrade to Gemini Pro.

openclaw config set provider google
openclaw config set model gemini-2.5-pro
openclaw config set apiKey your-google-ai-key