AI on demand: MiniMax

Calling the model

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

# Set the desired model
MODEL_ID=MiniMaxAI/MiniMax-M2.5

curl -s https://llm.stoney-cloud.com/v1/chat/completions \
  -H "Authorization: Bearer $STONEY_KEY" \
  -H "Content-Type: application/json"   \
  -d '{
    "model": "'"$MODEL_ID"'",
    "messages": [
      {"role": "user", "content": "Hello."}
    ],
    "max_tokens": 100
  }' \
  | jq .

Example output:

{
  "id": "chatcmpl-9f55d44ee87ed4e7",
  "object": "chat.completion",
  "created": 1775141698,
  "model": "MiniMaxAI/MiniMax-M2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "<think>The user has simply greeted me with \"Hello.\" This is a simple greeting, so I should respond in a friendly and welcoming manner.\n</think>\n\nHello! How can I help you today?",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning": null
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "prompt_tokens": 41,
    "total_tokens": 80,
    "completion_tokens": 39,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "kv_transfer_params": null
}