AI on demand: NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B

Calling the model

# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B

# Set your prompt:
PROMPT='Hello.'

# Set maximum amount of tokens:
MAX_TOKENS=100

curl https://llm.stoney-cloud.com/v1/chat/completions \
        --silent --fail --show-error \
        --header "Authorization: Bearer $STONEY_KEY" \
        --header 'Content-Type: application/json'   \
        --data '{
                "model": "'"$MODEL"'",
                "messages": [
                        {"role": "user", "content": "'"$PROMPT"'"}
                ],
                "max_tokens": '"$MAX_TOKENS"'
        }' \
        | jq

Example output:

{
  "id": "chatcmpl-af98aba2443fdd6f",
  "object": "chat.completion",
  "created": 1778156848,
  "model": "NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello! How can I assist you today?",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning": "We need to respond with a friendly greeting. No special instructions.\n\n"
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "prompt_tokens": 18,
    "total_tokens": 43,
    "completion_tokens": 25,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "kv_transfer_params": null
}