Models · Hardware · Providers
Ask anything about running AI —
then see the data behind the answer.
Every answer is grounded in our live database of 481 models, 71 devices from data-centre GPUs to phones, and 1,937 provider price listings. We re-read each listing on its own schedule — the newest 1 hour ago, the oldest 3 months ago.
no sign-in · answers grounded in live catalogue data
01481 entries
Models
Every open model, fully specced.
VRAM per quant, estimated tokens/sec, benchmarks, licenses — synced from primary sources daily.
0271 entries
Hardware
GPUs, Macs and phones, ranked for AI.
What fits, how fast it runs, and what to buy next — from an RTX 5090 down to the phone in your pocket.
0388 providers
Providers
Hosted inference, priced daily.
1937 live offers with per-token pricing, served quants, context limits and privacy terms.
Latest releases & changes
All news →Host Wafer (mxfp4) raised DeepSeek V4 Flash cache-read pricing by 1438%1 hour agoHost Inceptron cut GLM 5.2 input pricing by 10%7 hours agoHost Reka raised Qwen3.6 27B output pricing by 7%7 hours agoMiniMax M3.1 Flash listed7 hours agoGLM 5.3 Flash repriced across 5 hosts: OpenInference output down 81%, Sail Research (US region) output up 67%19 hours agoGLM 5.3 repriced across 5 hosts: Sail Research (US region) input down 33%, output up 100%19 hours ago
