Skill3 steps

Model Shootout

Run one prompt across several models and compare them side by side.

How it runs

One call, every step handled.

Pick up to eight models, send one prompt and get every result back in a single grid with timing, cost and an aesthetic score for each. The fastest way to choose the right model for a job.

Every intermediate result is kept with the run, so you can inspect a step, reuse its output or rerun it with different settings.

Input
- Prompt
- Models to compare
01
Fan out the promptRouter
02
Generate in parallelUp to eight models you choose
03
Score and rankAesthetic scorer
OutputA comparison grid with scores

Run it

Call the skill by name.

Send the inputs, get back a run you can wait on or follow with a webhook. The same skill is available in the studio and to AI agents through the MCP server.

You get back

A comparison grid with scores

run.sh

curl https://api.monogram.dev/v1/skills/model-shootout/runs \
  -H "Authorization: Bearer $MONOGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "prompt": "A jazz trumpeter under a single spotlight",
      "models": [
        "bfl/flux-2-pro",
        "google/gemini-3-pro-image",
        "bytedance/seedream-4.5",
        "openai/gpt-image-1.5"
      ]
    }
  }'