IBM Granite 4.0

curl -X POST "https://api.runpod.ai/v2/granite-4-0-h-small/runsync" \
  -H "Authorization: Bearer $RUNPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "messages": [
        {
          "role": "system",
          "content": "You are a helpful assistant. Please ensure responses are professional, accurate, and safe."
        },
        {
          "role": "user",
          "content": "What is Runpod?"
        }
      ],
      "sampling_params": {
        "max_tokens": 512,
        "temperature": 0.7,
        "seed": -1,
        "top_k": -1,
        "top_p": 1
      }
    }
  }'

import requests

response = requests.post(
    "https://api.runpod.ai/v2/granite-4-0-h-small/runsync",
    headers={
        "Authorization": f"Bearer {RUNPOD_API_KEY}",
        "Content-Type": "application/json",
    },
    json={
        "input": {
            "messages": [
                {
                    "role": "system",
                    "content": "You are a helpful assistant. Please ensure responses are professional, accurate, and safe.",
                },
                {"role": "user", "content": "What is Runpod?"},
            ],
            "sampling_params": {
                "max_tokens": 512,
                "temperature": 0.7,
                "seed": -1,
                "top_k": -1,
                "top_p": 1,
            },
        }
    },
)

result = response.json()
print(result["output"])

const response = await fetch(
  "https://api.runpod.ai/v2/granite-4-0-h-small/runsync",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${RUNPOD_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      input: {
        messages: [
          {
            role: "system",
            content: "You are a helpful assistant. Please ensure responses are professional, accurate, and safe.",
          },
          { role: "user", content: "What is Runpod?" },
        ],
        sampling_params: {
          max_tokens: 512,
          temperature: 0.7,
          seed: -1,
          top_k: -1,
          top_p: 1,
        },
      },
    }),
  }
);

const result = await response.json();
console.log(result.output);

{
  "id": "sync-a1b2c3d4-e5f6-7890-abcd-ef1234567890-u1",
  "status": "COMPLETED",
  "delayTime": 15,
  "executionTime": 2345,
  "workerId": "oqk7ao1uomckye",
  "output": {
    "choices": [
      {
        "tokens": [
          "Runpod is a cloud computing platform that provides GPU resources for AI and machine learning workloads..."
        ]
      }
    ],
    "cost": 0.00185,
    "usage": {
      "input": 35,
      "output": 150
    }
  }
}

{
  "id": "sync-a1b2c3d4-e5f6-7890-abcd-ef1234567890-u1",
  "status": "FAILED",
  "error": "Invalid messages format"
}