GPT-5.4 Pro

Text Generation • OpenAI • Proxied

GPT-5.4 Pro uses OpenAI's Responses API with built-in tools, improved reasoning, and stateful context management.

Model Info
Context Window ↗	1,000,000 tokens
Terms and License	link ↗
More information	link ↗
Pricing	View pricing in the Cloudflare dashboard ↗

Usage

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input: 'What are the three laws of thermodynamics?',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "input": "What are the three laws of thermodynamics?"
}

{}

Examples

With Instructions — Using instructions to set context

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input: 'How do I read a JSON file in Python?',
    instructions: 'You are a helpful coding assistant specializing in Python.',
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "input": "How do I read a JSON file in Python?",
    "instructions": "You are a helpful coding assistant specializing in Python."
}

{}

Multi-turn Conversation — Continuing a conversation with message array

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input: [
      {
        role: 'user',
        content:
          'I need help planning a road trip from San Francisco to Los Angeles.',
      },
      {
        role: 'assistant',
        content:
          "I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?",
      },
      {
        role: 'user',
        content: 'Yes, what are some good places to stop?',
      },
    ],
    max_output_tokens: 150,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "input": [
        {
            "role": "user",
            "content": "I need help planning a road trip from San Francisco to Los Angeles."
        },
        {
            "role": "assistant",
            "content": "I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?"
        },
        {
            "role": "user",
            "content": "Yes, what are some good places to stop?"
        }
    ],
    "max_output_tokens": 150
}

{}

Temperature Control — Using temperature for creative responses

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input: 'Write a haiku about artificial intelligence',
    temperature: 1,
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "input": "Write a haiku about artificial intelligence",
    "temperature": 1
}

{}

With Reasoning — Using reasoning effort for complex problems

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input:
      'Solve this problem step by step: A train leaves Chicago at 60mph heading east. Another train leaves New York at 80mph heading west. They are 900 miles apart. When do they meet?',
    reasoning: {
      effort: 'medium',
    },
  },
  {
    gateway: { id: 'default' },
  }
)
console.log(response)

Input / Output JSON

Input
Output

{
    "input": "Solve this problem step by step: A train leaves Chicago at 60mph heading east. Another train leaves New York at 80mph heading west. They are 900 miles apart. When do they meet?",
    "reasoning": {
        "effort": "medium"
    }
}

{}

▶input

one ofrequired

instructions

string

temperature

numberminimum: 0maximum: 2

max_output_tokens

numberexclusiveMinimum: 0

top_p

numberminimum: 0maximum: 1

stream

boolean

▶tools[]

array

tool_choice

▶text{}

object

▶reasoning{}

object

string

object

stringconst: response

created_at

number

model

string

▶output[]

array

output_text

string

status

stringenum: in_progress, completed, failed, incomplete

▶usage{}

object

API Schemas (Raw)

Input

Output