models-dev
Query AI model specifications, pricing, and capabilities from models.dev database. Use when users ask about AI model parameters (context window, token limits, cost per token), model comparisons, provider information, or need to look up specific model IDs for AI SDK integration. Triggers on queries like "What's the context window for GPT-4o?", "Compare Claude vs GPT", "How much does Gemini Pro cost?", "List OpenAI models", or "What models support tool calling?".
Best use case
models-dev is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Query AI model specifications, pricing, and capabilities from models.dev database. Use when users ask about AI model parameters (context window, token limits, cost per token), model comparisons, provider information, or need to look up specific model IDs for AI SDK integration. Triggers on queries like "What's the context window for GPT-4o?", "Compare Claude vs GPT", "How much does Gemini Pro cost?", "List OpenAI models", or "What models support tool calling?".
Teams using models-dev should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/models-dev/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How models-dev Compares
| Feature / Agent | models-dev | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Query AI model specifications, pricing, and capabilities from models.dev database. Use when users ask about AI model parameters (context window, token limits, cost per token), model comparisons, provider information, or need to look up specific model IDs for AI SDK integration. Triggers on queries like "What's the context window for GPT-4o?", "Compare Claude vs GPT", "How much does Gemini Pro cost?", "List OpenAI models", or "What models support tool calling?".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Models.dev - AI Model Information Query Query comprehensive AI model specifications from the models.dev open-source database. ## Usage Run the script at `scripts/fetch_models.py`: ```bash # List all providers python scripts/fetch_models.py --providers # Search models by name or ID python scripts/fetch_models.py --search <query> # Get specific model info python scripts/fetch_models.py <model_id> # List models from a provider python scripts/fetch_models.py --provider <provider_name> # Compare two models python scripts/fetch_models.py --compare <model_id_1> <model_id_2> ``` ## Examples ```bash # Search for Claude models python scripts/fetch_models.py --search claude # Get GPT-4o details python scripts/fetch_models.py gpt-4o # List Anthropic models python scripts/fetch_models.py --provider anthropic # Compare Claude Sonnet 3.7 vs GPT-4o python scripts/fetch_models.py --compare claude-3-7-sonnet-20250219 gpt-4o ``` ## Available Data Each model includes (when available): - **Model ID**: Identifier for AI SDK integration - **Provider**: Company/platform offering the model - **SDK Package**: npm package for AI SDK - **Capabilities**: Reasoning, Tool Calling, Structured Output, Attachments, Temperature - **Modalities**: Input/output types (text, image, audio, video, pdf) - **Limits**: Context window, max input/output tokens - **Cost**: Per-million token pricing (input, output, cache, reasoning) - **Dates**: Knowledge cutoff, release date, last updated - **Status**: alpha, beta, deprecated (if applicable) - **Open Weights**: Whether model weights are publicly available ## API Source Data fetched from `https://models.dev/api.json` - a community-maintained open-source database.
Related Skills
ios-foundation-models-diag
Use when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems, unsupported language, or unexpected output. Systematic diagnostics with production crisis defense.
axiom-foundation-models
Use when implementing on-device AI with Apple's Foundation Models framework — prevents context overflow, blocking UI, wrong model use cases, and manual JSON parsing when @Generable should be used. iOS 26+, macOS 26+, iPadOS 26+, axiom-visionOS 26+
avalonia-viewmodels-zafiro
Optimal ViewModel and Wizard creation patterns for Avalonia using Zafiro and ReactiveUI.
defining-typescript-models
Defines standard TypeScript interfaces for Appwrite Collections. Use when creating new models for Tours, Users, or Bookings to ensure full type safety.
sqlmodel-task-models
This skill should be used when defining a robust, type-safe, and async-compatible database schema for the Todo application using SQLModel, ensuring compatibility with Better Auth and optimized for PostgreSQL.
pydantic-models-py
Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation ...
API Models
Your approach to handling API models. Use this skill when working on files where API models comes into play.
ai-models
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
agent-selecting-models
Guidance for selecting appropriate AI model (sonnet vs haiku) based on task complexity, reasoning requirements, and performance needs. Use when implementing agents or justifying model selection.
adding-models
Guide for adding new LLM models to Letta Code. Use when the user wants to add support for a new model, needs to know valid model handles, or wants to update the model configuration. Covers models.json configuration, CI test matrix, and handle validation.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
mcp-create-declarative-agent
Skill converted from mcp-create-declarative-agent.prompt.md