Ai Models

Quick reference for model IDs, pricing, and capabilities across Claude, OpenAI, Gemini, Eleven Labs, and Replicate. Saves you from digging through docs when you need to know whether to use Haiku or Sonnet, or what the latest GPT-4.1 model string actually is. Includes code examples and a selection matrix that maps tasks to recommended models. Updated December 2025, which matters because model names change constantly and you don't want to be calling deprecated endpoints. Most useful when you're starting a new project or optimizing costs, less useful if you already have your model choices locked in.

skills.sh installs: 201
GitHub stars: 685
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add alinaqi/claude-bootstrap --skill ai-models --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Models Reference Skill

Last Updated: December 2025

Philosophy

Use the right model for the job. Bigger isn't always better - match model capabilities to task requirements. Consider cost, latency, and accuracy tradeoffs.

Model Selection Matrix

Task	Recommended	Why
Complex reasoning	Claude Opus 4.5, o3, Gemini 3 Pro	Highest accuracy
Fast chat/completion	Claude Haiku, GPT-4.1 mini, Gemini Flash	Low latency, cheap
Code generation	Claude Sonnet 4.5, Codestral, GPT-4.1	Strong coding
Vision/images	Claude Sonnet, GPT-4o, Gemini 3 Pro	Multimodal
Embeddings	text-embedding-3-small, Voyage	Cost-effective
Voice synthesis	Eleven Labs v3, OpenAI TTS	Natural sounding
Image generation	FLUX.2, DALL-E 3, SD 3.5	Different styles