Update gemini docs

[MinhAnh248]

Change 'Enable the Gemini Language API' to 'Enable the Gemini API'

[github-actions]

Docker Build Status

Build Successful for PR #116

Build Details

• Platforms: linux/amd64, linux/arm64
• Tags: ghcr.io/versuscontrol/ai-infrastructure-agent:pr-116
• Commit: 1b02662
• Version: pr-116

Next Steps

• Image build verification passed
• Ready for code review and merge
• Upon merge to main, dev image will be built and pushed automatically

---

*Updated at: *

[MinhAnh248]

Closes #98

[hoalongnatsu]

Thanks for the PR! The model names and details reference outdated 1.5/2.0 series. Please update to the Gemini 2.5 series per https://ai.google.dev/gemini-api/docs/models. Below is a sample table for docs/api-key-setup/gemini-api-setup.md to replace the current one, focusing on stable models for infrastructure tasks. Also, update pricing from https://ai.google.dev/pricing, and use https://generativelanguage.googleapis.com/v1/models/gemini-2.5-flash:generateContent for CURL tests. Remove deprecated models like gemini-1.0-pro or gemini-1.5-*.

Sample Model Table

Model	Best For	Speed	Capabilities
gemini-2.5-pro	Complex reasoning, production-ready	Medium	Multimodal (audio/images/video/text/PDF), caching, code execution, function calling, search grounding, structured outputs, thinking, URL context
gemini-2.5-flash	Fast responses, balanced performance	Fast	Multimodal (text/images/video/audio), caching, code execution, function calling, search grounding, structured outputs, thinking, URL context
gemini-2.5-flash-lite	Ultra-fast, cost-efficient for simple tasks	Very Fast	Multimodal (text/image/video/audio/PDF), caching, code execution, function calling, search grounding, structured outputs, thinking, URL context

Recommended: Use gemini-2.5-pro for production, gemini-2.5-flash or gemini-2.5-flash-lite for development/testing. Let me know if you need help with the diff!