Collections

Curated shortlists of models and providers, grouped by what you're building. A fast way in when you know the job but not the model.

Best LLMs for Coding

Models with strong code-generation capabilities for autocompletion, refactoring, and agentic coding.

Models tuned for step-by-step reasoning, math, planning, and complex problem solving.

Multimodal models that understand images, documents, screenshots, and charts.

Openly licensed models you can self-host or run locally, from Apache 2.0 to MIT and beyond.

Low-cost models under $1 per million tokens (input + output) for budget-conscious workloads.

Models with 200K+ token context windows for large documents, codebases, and RAG.

Models that produce vector embeddings for semantic search, RAG, and clustering.

Inference providers exposing an OpenAI-compatible API — swap the base URL and keep your SDK.