GPT-5.4 pro

Text Generation • OpenAI

openai/gpt-5.4-pro

• Third-party
• Zero data retention

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

Usage

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

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-5.4-pro",
  "input": "What are the three laws of thermodynamics?"
}'

The **three laws of thermodynamics** usually mean:

1. **First Law — Conservation of Energy**  
   Energy cannot be created or destroyed, only transferred or transformed.  
   - In thermodynamics: the change in a system’s internal energy equals heat added to the system minus work done by the system.

2. **Second Law — Entropy Increases**  
   In any natural process, the total entropy of an isolated system tends to increase.  
   - This means energy spontaneously spreads out, and no heat engine can be 100% efficient.
   - Heat naturally flows from hot objects to cold ones, not the reverse without input of work.

3. **Third Law — Entropy at Absolute Zero**  
   As temperature approaches **absolute zero** (0 K), the entropy of a perfect crystal approaches zero.  
   - A consequence is that absolute zero cannot be reached in a finite number of steps.

Small note: thermodynamics also has a **Zeroth Law**, which is often listed before these:
- If system A is in thermal equilibrium with B, and B is in thermal equilibrium with C, then A is in thermal equilibrium with C.  
- This is the basis for the concept of **temperature**.

If you want, I can also give a **one-line intuitive version** of each law.

{
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1777054203,
  "created_at": 1777054122,
  "error": null,
  "frequency_penalty": 0,
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "id": "resp_00272dd8da5b37c90169ebb1aaeb288194a6e5ddeb7bb03dc8",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {},
  "model": "gpt-5.4-pro-2026-03-05",
  "moderation": null,
  "object": "response",
  "output": [
    {
      "id": "rs_00272dd8da5b37c90169ebb1faf90c81948fd9a67a37b4c209",
      "summary": [],
      "type": "reasoning"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "The **three laws of thermodynamics** usually mean:\n\n1. **First Law — Conservation of Energy**  \n   Energy cannot be created or destroyed, only transferred or transformed.  \n   - In thermodynamics: the change in a system’s internal energy equals heat added to the system minus work done by the system.\n\n2. **Second Law — Entropy Increases**  \n   In any natural process, the total entropy of an isolated system tends to increase.  \n   - This means energy spontaneously spreads out, and no heat engine can be 100% efficient.\n   - Heat naturally flows from hot objects to cold ones, not the reverse without input of work.\n\n3. **Third Law — Entropy at Absolute Zero**  \n   As temperature approaches **absolute zero** (0 K), the entropy of a perfect crystal approaches zero.  \n   - A consequence is that absolute zero cannot be reached in a finite number of steps.\n\nSmall note: thermodynamics also has a **Zeroth Law**, which is often listed before these:\n- If system A is in thermal equilibrium with B, and B is in thermal equilibrium with C, then A is in thermal equilibrium with C.  \n- This is the basis for the concept of **temperature**.\n\nIf you want, I can also give a **one-line intuitive version** of each law.",
          "type": "output_text"
        }
      ],
      "id": "msg_00272dd8da5b37c90169ebb1fafad0819488ef71fbebf8527a",
      "phase": "final_answer",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 15,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 342,
    "output_tokens_details": {
      "reasoning_tokens": 67
    },
    "total_tokens": 357
  },
  "user": null
}

Examples

<details>

<summary>With Instructions — Using instructions to set context</summary>

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.',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "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."
}'

Use Python’s built-in `json` module.

### Read a JSON file into a Python object
```python
import json

with open("data.json", "r", encoding="utf-8") as f:
    data = json.load(f)

print(data)
```

### What you get back
`json.load()` converts JSON into normal Python types:

- JSON object → `dict`
- JSON array → `list`
- JSON string → `str`
- JSON number → `int` / `float`
- JSON true/false → `True` / `False`
- JSON null → `None`

### Example
If `data.json` contains:
```json
{
  "name": "Alice",
  "age": 30,
  "skills": ["Python", "SQL"]
}
```

Then:
```python
import json

with open("data.json", "r", encoding="utf-8") as f:
    data = json.load(f)

print(data["name"])    # Alice
print(data["skills"])  # ['Python', 'SQL']
```

### Handle errors safely
```python
import json

try:
    with open("data.json", "r", encoding="utf-8") as f:
        data = json.load(f)
except FileNotFoundError:
    print("File not found.")
except json.JSONDecodeError:
    print("Invalid JSON.")
```

### If you already have JSON as a string
Use `json.loads()` instead:
```python
import json

text = '{"name": "Alice", "age": 30}'
data = json.loads(text)
print(data)
```

If you want, I can also show how to **write JSON back to a file**.

{
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1777054145,
  "created_at": 1777054123,
  "error": null,
  "frequency_penalty": 0,
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "id": "resp_00e5a81e42bf0bda0169ebb1ab449c8190a0d57802b4aebebd",
  "incomplete_details": null,
  "instructions": "You are a helpful coding assistant specializing in Python.",
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {},
  "model": "gpt-5.4-pro-2026-03-05",
  "moderation": null,
  "object": "response",
  "output": [
    {
      "id": "rs_00e5a81e42bf0bda0169ebb1c0e57881909eaf01efa0557a43",
      "summary": [],
      "type": "reasoning"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "Use Python’s built-in `json` module.\n\n### Read a JSON file into a Python object\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n    data = json.load(f)\n\nprint(data)\n```\n\n### What you get back\n`json.load()` converts JSON into normal Python types:\n\n- JSON object → `dict`\n- JSON array → `list`\n- JSON string → `str`\n- JSON number → `int` / `float`\n- JSON true/false → `True` / `False`\n- JSON null → `None`\n\n### Example\nIf `data.json` contains:\n```json\n{\n  \"name\": \"Alice\",\n  \"age\": 30,\n  \"skills\": [\"Python\", \"SQL\"]\n}\n```\n\nThen:\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n    data = json.load(f)\n\nprint(data[\"name\"])    # Alice\nprint(data[\"skills\"])  # ['Python', 'SQL']\n```\n\n### Handle errors safely\n```python\nimport json\n\ntry:\n    with open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n        data = json.load(f)\nexcept FileNotFoundError:\n    print(\"File not found.\")\nexcept json.JSONDecodeError:\n    print(\"Invalid JSON.\")\n```\n\n### If you already have JSON as a string\nUse `json.loads()` instead:\n```python\nimport json\n\ntext = '{\"name\": \"Alice\", \"age\": 30}'\ndata = json.loads(text)\nprint(data)\n```\n\nIf you want, I can also show how to **write JSON back to a file**.",
          "type": "output_text"
        }
      ],
      "id": "msg_00e5a81e42bf0bda0169ebb1c0e7608190b3928d22f252a21a",
      "phase": "final_answer",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 30,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 397,
    "output_tokens_details": {
      "reasoning_tokens": 35
    },
    "total_tokens": 427
  },
  "user": null
}

</details>

<details>

<summary>Multi-turn Conversation — Continuing a conversation with message array</summary>

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input: [
      {
        content: 'I need help planning a road trip from San Francisco to Los Angeles.',
        role: 'user',
      },
      {
        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: 'assistant',
      },
      { content: 'Yes, name three good stops in one short sentence each.', role: 'user' },
    ],
    max_output_tokens: 16000,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-5.4-pro",
  "input": [
    {
      "content": "I need help planning a road trip from San Francisco to Los Angeles.",
      "role": "user"
    },
    {
      "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": "assistant"
    },
    {
      "content": "Yes, name three good stops in one short sentence each.",
      "role": "user"
    }
  ],
  "max_output_tokens": 16000
}'