CLI and TUI for browsing AI models and tracking coding agents. Quickly look up context windows, pricing, capabilities, and more for 2000+ models across 75+ providers. Access changelog information across 12+ coding agents.
git clone https://github.com/arimxyer/models.gitModels is a terminal application that centralizes information about AI models, benchmarks, coding agents, and provider status pages. It aggregates ~4,000 models across 85+ providers from models.dev with filtering by capability, price, context, and provider category. The tool includes ~1,000 benchmark entries from four sources (Artificial Analysis, Epoch AI, Arena, LLM Stats) for head-to-head model comparison using scatter plots and radar charts. You can track 11+ coding agents with automatic version detection, GitHub release integration, and styled changelogs. Additionally, it monitors live health status for 22 AI providers across 7 status page platforms, displaying incidents and maintenance information in a unified dashboard.
1. **Install the CLI/TUI tool**: Run `pip install ai-models-cli` or use the provided executable for your OS. For TUI, launch with `ai-models tui`. 2. **Search for models**: Use the search command `ai-models search --query "Claude 3.5 Sonnet"` or browse interactively in the TUI. 3. **Compare models**: Use `ai-models compare --model1 "Claude 3.5 Sonnet" --model2 "GPT-4o"` to generate a side-by-side comparison table. 4. **Check coding agent updates**: Run `ai-models changelog --agent "Cursor"` to view recent changes and version history. 5. **Export results**: Use `ai-models export --format csv` to save comparisons for further analysis in tools like Excel or Google Sheets. **Tips:** - Use the `--detailed` flag for in-depth technical specs (e.g., `ai-models compare --model1 "Claude 3.5 Sonnet" --detailed`). - Filter models by use case (e.g., `--use-case coding`) to narrow down options quickly. - Bookmark frequently used models for faster access in future sessions.
Compare AI models by context window, pricing, and capabilities across multiple providers
Track coding agent versions and changelogs for Claude Code, Cursor, and other tools
Analyze model performance benchmarks from multiple independent sources
Monitor AI provider status pages and service health in real-time
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/arimxyer/modelsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use the CLI/TUI tool to browse AI models and coding agents. Look up the [MODEL_NAME] model from [PROVIDER] and compare its context window, pricing, and capabilities with [ALTERNATIVE_MODEL] from [ALTERNATIVE_PROVIDER]. Check the changelog for [CODING_AGENT] to see recent updates. Summarize the key differences in a table format.
### Model Comparison: Claude 3.5 Sonnet vs. GPT-4o | Feature | Claude 3.5 Sonnet (Anthropic) | GPT-4o (OpenAI) | |------------------------|-------------------------------|--------------------------| | **Context Window** | 200,000 tokens | 128,000 tokens | | **Pricing (Input)** | $3.00 / 1M tokens | $5.00 / 1M tokens | | **Pricing (Output)** | $15.00 / 1M tokens | $15.00 / 1M tokens | | **Max Output Length** | 8,192 tokens | 4,096 tokens | | **Multimodal Support** | Yes (text, images) | Yes (text, images, audio)| | **Strengths** | Coding, reasoning, long docs | Creativity, speed | ### Coding Agent Changelog: Cursor **Recent Updates (v0.32.0 - v0.34.0):** - Added native support for Claude 3.5 Sonnet with 200K context window. - Improved codebase indexing speed by 40% for large repositories. - Fixed a bug where multi-file edits would occasionally overwrite changes. - Added real-time collaboration features for team-based coding. **Recommendation:** If your workflow involves large codebases or long documents, Claude 3.5 Sonnet is the better choice due to its superior context window and competitive pricing. For rapid prototyping or creative tasks, GPT-4o may be preferable.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan