100+ models. One catalog.
Compare pricing, latency, context windows, and capabilities across every major LLM provider.
Reasoning + coding — best for general + code.
Lowest-cost workhorse — best for high-volume tasks.
Writing + agents — best for agents + writing.
Deep reasoning + coding — best for complex agentic work.
Multimodal + long context — best for long context, vision.
Fast multimodal — best for pdf, audio, video at scale.
Realtime + tools — best for search-grounded.
Open-weight reasoning — best for math, logic, planning.
Cheapest capable API — best for bulk processing.
Open weights — best for customizable, self-host.
Lowest latency — best for realtime ux.
Enterprise EU — best for eu deployment.
Cost-efficient multilingual — best for multilingual apps.
RAG + tools — best for enterprise rag.