ai-models

Reference current AI model IDs, pricing, and usage patterns for major LLM and media APIs.

Updated Jan 16, 2026
One-click install
npx skills add https://github.com/dudqks0319-cpu/antigravity-skills --skill ai-models-dudqks0319-cpu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-models
Source: https://github.com/dudqks0319-cpu/antigravity-skills/tree/main/ai-models
Command: npx skills add https://github.com/dudqks0319-cpu/antigravity-skills --skill ai-models-dudqks0319-cpu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Choosing the right AI model and keeping model IDs current is difficult when providers release new versions frequently. This Skill provides an up-to-date reference of model identifiers, pricing, context limits, and code examples across Anthropic, OpenAI, Google, Eleven Labs, Replicate, Stability AI, Mistral, and Voyage AI. ## Core Features & Use Cases - Model Selection Matrix: Maps tasks like reasoning, code generation, vision, embeddings, and voice synthesis to recommended models with cost and latency tradeoffs. - Provider-Specific References: Lists current model IDs, TypeScript usage examples, and selection guidance for each major AI provider. - Cost Comparison Tables: Compares per-token pricing across providers at cheap, mid, and premium tiers. - Use Case: When building a chatbot, consult this Skill to pick between Claude Sonnet 4.5, GPT-4.1, and Gemini 2.5 Flash based on context length, cost, and latency requirements, then copy the correct model ID and SDK snippet directly into your code. ## Quick Start Ask which AI model to use for your task and request the current model ID and a usage example for your chosen provider.

Frequently Asked Questions about ai-models

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

FAQPage Schema
How do I choose the right AI model for my task?▼

Match the model to your task requirements using the selection matrix: Claude Opus 4.5 or o3 for complex reasoning, Claude Sonnet 4.5 or GPT-4.1 for code generation, and Gemini Flash or GPT-4.1-mini for fast, high-volume tasks. Consider cost, latency, and context length tradeoffs.

What is the latest Claude model ID for the Anthropic API?▼

The flagship model is claude-opus-4-5-20251101, while claude-sonnet-4-5-20250929 is the balanced default for most tasks. For high-volume, low-cost work, use claude-haiku-3-5-20241022.

Which AI model has the largest context window?▼

Gemini 2.5 Pro and Gemini 3 Pro support up to 2M tokens, the largest among listed providers. GPT-4.1 supports 1M tokens, while Claude models support 200K tokens.

OpenAI vs Anthropic vs Gemini for code generation?▼

Claude Sonnet 4.5, GPT-4.1, and Codestral 2508 are all strong for code generation. Claude Sonnet 4.5 is the recommended default for coding tasks, while Codestral specializes in code across 80+ languages at faster speeds.

What is the cheapest LLM for high-volume tasks?▼

Gemini 2.5 Flash Lite is the cheapest at roughly $0.04/$0.15 per 1M tokens. GPT-4.1-nano and Claude Haiku 3.5 are also low-cost options for classification, extraction, and simple high-volume tasks.

Which text-to-speech model works for real-time voice agents?▼

Eleven Labs eleven_flash_v2_5 is designed for real-time conversational AI with latency under 75ms across 32 languages. For pre-rendered audio where quality matters most, use eleven_v3 instead.