curl --request POST \
  --url https://api.iotools.cloud/v1/tool/gpu-vram-calculator \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "modelPreset": "mistral-7b",
  "mode": "inference",
  "precision": "fp16",
  "batchSize": "1",
  "seqLen": "4096"
}
'

{
  "tool": "gpu-vram-calculator",
  "tool_version": "1.0.1",
  "outputs": {
    "breakdown": [
      {
        "component": "Model weights",
        "memory": "13.49 GB",
        "share": "78.4%"
      },
      {
        "component": "KV cache",
        "memory": "2.00 GB",
        "share": "11.6%"
      },
      {
        "component": "Activations",
        "memory": "0.16 GB",
        "share": "0.9%"
      },
      {
        "component": "Framework overhead",
        "memory": "1.56 GB",
        "share": "9.1%"
      },
      {
        "component": "Total VRAM",
        "memory": "17.21 GB",
        "share": "100%"
      }
    ],
    "gpuFit": [
      {
        "gpu": "RTX 4060 Ti 16GB",
        "vram": "16 GB",
        "fit": "Over (108%)",
        "gpus-needed": "2 GPUs"
      },
      {
        "gpu": "RTX 4090 24GB",
        "vram": "24 GB",
        "fit": "Fits (72%)",
        "gpus-needed": "1 GPU"
      },
      {
        "gpu": "RTX 5090 32GB",
        "vram": "32 GB",
        "fit": "Fits (54%)",
        "gpus-needed": "1 GPU"
      },
      {
        "gpu": "A100 40GB",
        "vram": "40 GB",
        "fit": "Fits (43%)",
        "gpus-needed": "1 GPU"
      },
      {
        "gpu": "A100 / H100 80GB",
        "vram": "80 GB",
        "fit": "Fits (22%)",
        "gpus-needed": "1 GPU"
      },
      {
        "gpu": "H200 141GB",
        "vram": "141 GB",
        "fit": "Fits (12%)",
        "gpus-needed": "1 GPU"
      }
    ]
  },
  "credits_used": 3,
  "credits_remaining": null
}