llm_fit_finder

Parameters schema

{
  "type": "object",
  "properties": {
    "mode": {
      "type": "string",
      "description": "cloud (API models) or local (Ollama/self-hosted). Default: cloud"
    },
    "top_n": {
      "type": "number",
      "description": "Number of recommendations to return (default: 5)"
    },
    "vram_gb": {
      "type": "number",
      "description": "GPU VRAM in GB (only for mode=local). Default: 16"
    },
    "features": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Required features: vision, function_calling, json_mode, streaming, reasoning"
    },
    "use_case": {
      "type": "string",
      "description": "Primary use case: chatbot | code | rag | summarization | classification | reasoning | agents | multilingual"
    },
    "max_budget": {
      "type": "number",
      "description": "Maximum monthly budget in USD (based on tokens_per_day)"
    },
    "quantization": {
      "type": "string",
      "description": "Quantization (only for mode=local): Q4_K_M | Q8_0 | FP16. Default: Q4_K_M"
    },
    "tokens_per_day": {
      "type": "number",
      "description": "Estimated daily token volume (default: 100000)"
    }
  }
}

No endpoints wrapped at confidence ≥ 0.70.

Parent server