Model Arena
Same prompt, N models: compare top LLMs side by side with streaming, code preview, latency and cost, plus an image arena.
Each demo runs on the same API and compute you build with. Open one, then read the docs.
Built by the GMI Cloud community and GMI DevRel. 49 demos, each one a small app that calls GMI inference and returns a result.
Same prompt, N models: compare top LLMs side by side with streaming, code preview, latency and cost, plus an image arena.
A whole NestJS monorepo (450K or 1.39M tokens) in one Grok 4.6 request: cross-module answers with file paths, and the bill with its 200K price step.
A needle-in-a-haystack test: up to 800K tokens of synthetic documents in one request, and the tile the model quotes lights up.
Drop a GitHub URL. Get an architectural map: import graph, hotspots, layers, Mermaid diagrams, and a reasoning model that explains any file. By Amitpandey88.
Browse 300+ models, build schema requests, and view results inline. By yannan000.
Run and monitor self-hosted coding agents with live sessions and tool calls. By tao12345666333.
Estimate what a workload costs on GMI Cloud inference: pick models, set tokens per request and traffic, compare totals.