Model Radar

Pings and ranks 130+ free coding LLM models across 17 providers by latency in real-time.

Scans free coding LLM models across providers including NVIDIA NIM, Groq, Cerebras, SambaNova, and OpenRouter to measure availability and latency. Ranks models by tier based on SWE-bench Verified scores and helps agents select the fastest available model for code generation tasks.