Models · Hardware · Providers
Ask anything about running AI —
then see the data behind the answer.
Every answer is grounded in our live database of 376 models, 71 devices from data-centre GPUs to phones, and provider pricing synced 59m ago.
01376 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.
0379 providers
Providers
Hosted inference, priced daily.
1547 live offers with per-token pricing, served quants, context limits and privacy terms.
Latest releases & changes
All news →DeepInfra raised DeepSeek V3.1 Terminus pricing by 8%60m agoChutes cut Kimi K3 pricing by 80%60m agoOpenRouter cut Qwen2.5 VL 72B Instruct pricing by 69%1h agoOpenRouter raised Mistral Small 3.2 24B pricing by 25%1h agoOpenRouter raised MiniMax M2.7 pricing by 8%1h agoIonstream raised Qwen3 Coder Next pricing by 5%7h ago
