Find the Right AI Model

Anthropic's most intelligent model for complex reasoning, coding, and long-context tasks. Best-in-class for agentic workflows.

Anthropic's fastest and most compact model. Available free via OpenRouter with generous limits. Great for rapid prototyping.

OpenAI's flagship multimodal model. Handles vision, audio, and text with strong coding and reasoning capabilities.

OpenAI's flagship multimodal model. Handles vision, audio, and text with strong coding and reasoning capabilities.

Lightweight, fast, and free-tier accessible. Great for everyday coding tasks and API experimentation.

Google's most capable model with a massive 1M token context window. Excellent for document analysis and long-context reasoning.

Meta's powerful open-source model. Runs locally with strong coding and reasoning. Requires 32GB RAM for smooth inference.

Lightweight version of Llama 3.1. Runs on consumer hardware with 8GB RAM. Good balance of speed and quality for local use.

Efficient 7B model with excellent instruction-following. Runs on most consumer hardware and excels at coding tasks.

Alibaba's specialized coding model. Outperforms GPT-4o on many coding benchmarks while running locally on 16GB RAM.

Open-source reasoning model that rivals o1 performance. Free via API with exceptional math, logic, and coding capabilities.

Microsoft's tiny but capable model. Runs on 4GB RAM with no GPU required. Perfect for offline use on laptops.

Moonshot AI's reasoning model with very long context. Competitive with o1 on reasoning benchmarks with strong coding ability.

Meta's dedicated code generation model. Fine-tuned for programming tasks with support for 20+ languages. Runs locally.

Google's open model with strong general performance. Efficient enough to run on 8GB RAM with competitive benchmark scores.

Anthropic's most powerful model optimized for Claude Code. Exceptional at autonomous coding, multi-step reasoning, and research.