Skip to content
Cloudflare Docs
DirectoryAPISDKsChangelog
OpenAI logo

GPT-5.4 pro

Text Generation • OpenAI

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 Licenselink ↗
More informationlink ↗
Zero data retentionYes
Request formatsResponses
PricingView pricing in the Cloudflare dashboard ↗

Usage

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

Examples

With Instructions — Using instructions to set context
TypeScript
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)
 
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**.
Multi-turn Conversation — Continuing a conversation with message array
TypeScript
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)
 
- Monterey is great for the aquarium, Cannery Row, and ocean views.  
- San Luis Obispo is a fun lunch stop with a charming downtown and Mission Plaza.  
- Santa Barbara offers beaches, palm-lined streets, and an easy coastal break.
Temperature Control — Using temperature for creative responses
TypeScript
const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  { input: 'Write a haiku about artificial intelligence', temperature: 1 },
)
console.log(response)
 
Silent circuits dream  
Learning patterns in the dark  
Dawn wakes metal minds
With Reasoning — Using reasoning effort for complex problems
TypeScript
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' },
  },
)
console.log(response)
 
Step 1: Find their combined speed since they are moving toward each other.

- Train from Chicago: **60 mph**
- Train from New York: **80 mph**

Combined speed:

**60 + 80 = 140 mph**

Step 2: Use the distance formula:

\[
\text{time}=\frac{\text{distance}}{\text{speed}}
\]

\[
\text{time}=\frac{900}{140}
\]

\[
\text{time}=6.428571\text{ hours}
\]

Step 3: Convert the decimal part to minutes.

\[
0.428571 \times 60 \approx 25.7 \text{ minutes}
\]

So they meet after about:

**6 hours 26 minutes**

Final answer: **The trains meet about 6 hours 26 minutes after they leave.**

Parameters

instructions
string
temperature
numberminimum: 0maximum: 2
max_output_tokens
numberexclusiveMinimum: 0
top_p
numberminimum: 0maximum: 1
stream
boolean
tool_choice

API Schemas (Raw)

Input
Output