Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt

Use this file to discover all available pages before exploring further.

Model ID 
openai/gpt-5.4-mini
The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

​
API Usage

You can interact with the OpenAI GPT-5.4-mini model through various programming languages and methods. Below are examples showing how to use the model’s API.

​
API Examples

Generate a model response using the chat endpoint of OpenAI GPT-5.4-mini.

​
Create chat completion

The Chat Completions API endpoint will generate a model response from a list of messages comprising a conversation.

​
Default

curl https://api.gmi-serving.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [
      {
        "role": "developer",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

from openai import OpenAI

endpoint = "https://api.gmi-serving.com/v1/"
model_name = "openai/gpt-5.4-mini"

api_key = "<gmi-api-key>"

client = OpenAI(
    base_url=f"{endpoint}",
    api_key=api_key
)

completion = client.chat.completions.create(
    model=model_name,
    messages=[
        {
            "role": "user",
            "content": "What is the capital of France?",
        }
    ],
)

print(completion.choices[0].message)

​
Streaming

curl https://api.gmi-serving.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [
      {
        "role": "developer",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "stream": true
  }'

from openai import OpenAI

endpoint = "https://api.gmi-serving.com/v1/"
model_name = "openai/gpt-5.4-mini"

api_key = "<gmi-api-key>"

client = OpenAI(
    base_url=f"{endpoint}",
    api_key=api_key
)

completion = client.chat.completions.create(
  model=model_name,
  messages=[
    {"role": "developer", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  stream=True
)

for chunk in completion:
  print(chunk.choices[0].delta)

​
Image Input

curl https://api.gmi-serving.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "What is in this image?"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
            }
          }
        ]
      }
    ],
    "max_completion_tokens": 300
  }'

from openai import OpenAI

endpoint = "https://api.gmi-serving.com/v1/"
model_name = "openai/gpt-5.4-mini"

api_key = "<gmi-api-key>"

client = OpenAI(
    base_url=f"{endpoint}",
    api_key=api_key
)

completion = client.chat.completions.create(
    model=model_name,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
                    }
                },
            ],
        }
    ],
    max_completion_tokens=300,
)

print(response.choices[0])

​
Functions

curl https://api.gmi-serving.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [
      {
        "role": "user",
        "content": "What is the weather like in Boston today?"
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA"
              },
              "unit": {
                "type": "string",
                "enum": ["celsius", "fahrenheit"]
              }
            },
            "required": ["location"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'

from openai import OpenAI

endpoint = "https://api.gmi-serving.com/v1/"
model_name = "openai/gpt-5.4-mini"

api_key = "<gmi-api-key>"

client = OpenAI(
    base_url=f"{endpoint}",
    api_key=api_key
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
completion = client.chat.completions.create(
  model=model_name,
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(completion)

​
Python

import requests
import json

url = "https://api.gmi-serving.com/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer *************"
}

payload = {
    "model": "openai/gpt-5.4-mini",
    "messages": [
        {"role": "system", "content": "You are a helpful AI assistant"},
        {"role": "user", "content": "List 3 countries and their capitals."}
    ],
    "temperature": 0,
    "max_completion_tokens": 500
}

response = requests.post(url, headers=headers, json=payload)
print(json.dumps(response.json(), indent=2))

​
Create a model response

OpenAI’s most advanced interface for generating model responses. Supports text and image inputs, and text outputs. Create stateful interactions with the model, using the output of previous responses as input. Extend the model’s capabilities with built-in tools for file search, web search, computer use, and more. Allow the model access to external systems and data using function calling.

​
Default

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": "Tell me a three sentence bedtime story about a unicorn."
  }'

​
Streaming

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "instructions": "You are a helpful assistant.",
    "input": "Hello!",
    "stream": true
  }'

​
Reasoning

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": "How much wood would a woodchuck chuck?",
    "reasoning": {
      "effort": "low"
    }
  }'

​
Functions

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": "What is the weather like in Boston today?",
    "tools": [
      {
        "type": "function",
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
              "type": "string",
              "description": "Temperature unit",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location", "unit"]
        }
      }
    ],
    "tool_choice": "auto"
  }'

​
Image Input

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": [
      {
        "role": "user",
        "content": [
          {"type": "input_text", "text": "what is in this image?"},
          {
            "type": "input_image",
            "image_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"
          }
        ]
      }
    ]
  }'

​
File Input

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "input": [
      {
        "role": "user",
        "content": [
          {"type": "input_text", "text": "what is in this file?"},
          {
            "type": "input_file",
            "file_url": "https://www.berkshirehathaway.com/letters/2024ltr.pdf"
          }
        ]
      }
    ]
  }'

curl https://api.gmi-serving.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GMI_API_KEY" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "tools": [{ "type": "web_search_preview" }],
    "input": "What was a positive news story from today?"
  }'