recommend

Find the best Scenario platform/public model for a single generation task. Returns ranked models with real performance data (ELO, latency, cost) and explanations. Args: - capability: one of '3d23d', 'audio2audio', 'audio2txt', 'audio2video', 'img23d', 'img2img', 'img2txt', 'img2video', 'txt23d', 'txt2audio', 'txt2img', 'txt2txt', 'txt2video', 'video23d', 'video2audio', 'video2img', 'video2video' (optional — inferred from prompt) - prompt: the user's original intent (required) - priority: 'quality' | 'speed' | 'cost' (default 'quality') - max_cost_cu, max_latency_seconds: optional constraints - features: required features list - limit: how many to return (1-10, default 5) Returns: ranked list with per-model explanation, tradeoff, real performance numbers, suggested input params for model_run, and a `next_step` directive. When `next_step.type` is `ask_user`, present `next_step.question` and `next_step.options` to the user and wait for their choice before calling `model_run` — do not auto-select a model. When `next_step.type` is `proceed`, use `specialty` (if present) or the top `ranked` entry. `caveats` on a ranked entry flag uncertainty to confirm with the user before generating. Entries with `requires_plan_upgrade: true` need a subscription upgrade to the plan in `required_plan` before they can be run — keep them visible (mark with ✨), but do not call `model_run` with one until the user has upgraded. Don't use when: the request needs multiple generation steps (use plan_generation) or you need to search private/unlisted models (use search).

{
  "capability": "txt2img",
  "priority": "quality",
  "prompt": "photorealistic product shot for instagram",
  "limit": 3
}

{
  "summary": "For a photorealistic Instagram product shot at 1:1, GPT Image 2 leads on Arena ELO with strong prompt adherence; Gemini 3.0 Pro is the high-fidelity alternative; Grok Imagine Pro adds the best cost-to-quality ratio at this resolution.",
  "ranked": [
    {
      "model_id": "model_openai-gpt-image-2",
      "name": "GPT Image 2",
      "rank": 1,
      "explanation": "ELO 1510 (Arena rank #1, image_edit) and 11.7 CU at 2K make this the top quality choice for photoreal product imagery.",
      "tradeoff": "~65s p50 latency — plan for batch, not real-time.",
      "quality_elo": 1510,
      "speed_summary": "64.7s median",
      "cost_summary": "11.7 CU",
      "suggested_inputs": {
        "aspectRatio": "1:1",
        "numImages": 1
      },
      "key_insights": [
        "Strong prompt adherence on product copy and finishes",
        "Use elementsImage to lock identity across iterations"
      ]
    }
  ],
  "query": {
    "capability": "txt2img",
    "priority": "quality"
  },
  "platform_detected": "instagram_post — 1:1",
  "total_matching": 634
}