Skip to main content
fireconnect claude demo runs the same code-generation prompt through two models using your current FireConnect Claude profile. It then puts the results next to each other so you can judge speed, cost, and output quality yourself. The demo reads your active FireConnect Claude profile but does not modify ~/.claude/settings.json. Each side runs in a separate temporary working directory.

​
What you get

  1. Live terminal race: both models stream code in a split-pane TUI with real token counts and wall-clock timers.
  2. Browser comparison: both generated apps run side by side, with measured speed and cost at the bottom.
  3. Shareable artifacts: outputs land in ./fireconnect-demo/ (compare.html, result.json, stream logs).

​
Browser comparison

Side-by-side runnable apps with measured speed and cost:
FireConnect demo browser comparison page with two Tetris apps side by side and speed and cost metrics

Browser comparison from a real FireConnect demo run: two Tetris apps with measured speed and cost

​
Terminal race

Split-pane TUI while both models stream the same prompt:
Animated capture of a FireConnect split-pane terminal race between Claude Sonnet and GLM 5.2 Fast on a Tetris prompt

Real FireConnect demo race: GLM 5.2 Fast finishes while Claude Sonnet is still running

​
Prerequisites

  • FireConnect installed (overview)
  • Claude Code CLI (claude) on your PATH
  • Claude Code already connected with fireconnect claude
Both sides use the same authentication and routing as your existing FireConnect Claude setup. The demo only supports Claude Code today.

​
Run the demo

That runs the default Tetris preset: both sides get the same prompt to build a playable game in a single HTML file.
The old top-level fireconnect demo form is deprecated. Use fireconnect claude demo.

​
Try other presets

Presets: tetris (default), snake, or clock. You can also pass custom task text or use --prompt-file.

​
Pick the models

The defaults are opus on the left and glm-fast-latest on the right. Pass any available model or Claude alias from your connected profile.

​
Non-interactive / CI-friendly

​
Clean up

demo clean only removes directories that contain demo markers (result.json, compare.html, etc.), so it will not delete an unrelated folder you pointed --out at by mistake.

​
After the demo

Liked one of the models? Set it as your daily driver:
More IDs and latest vs fast guidance: Models. Want automatic cost routing instead of a fixed model? Try FireRouter:

​
How it works

  • Each side runs real claude -p in a separate temporary working directory, using your active FireConnect Claude profile with only the model changed.
  • Numbers in the comparison strip are measured from the run, not list-price estimates.
  • If one side fails to finish, the page says so instead of fabricating a winner.
  • Open compare.html from the output folder anytime. It inlines both apps and works offline.

​
Source

The demo ships with FireConnect: github.com/fw-ai/fireconnect

​
See also