Skip to content
Cloudflare Docs
DirectoryAPISDKsChangelog
OpenAI logo

GPT-5.5 pro

Text Generation • OpenAI

GPT-5.5 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-5.5-pro',
  { input: 'What are the three laws of thermodynamics?' },
)
console.log(response)
 
The **three laws of thermodynamics** are:

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.  
   \[
   \Delta U = Q - W
   \]

2. **Second Law — Entropy Increases**  
   In any natural process, the total entropy of an isolated system tends to increase.  
   Equivalently, heat flows spontaneously from hotter objects to colder ones, and no heat engine can be 100% efficient.

3. **Third Law — Absolute Zero Limit**  
   As temperature approaches absolute zero, the entropy of a perfect crystal approaches zero.  
   It also implies that absolute zero cannot be reached by any finite physical process.

There is also a **Zeroth Law**, often stated separately: if two systems are each in thermal equilibrium with a third system, they are in thermal equilibrium with each other. This is what makes temperature well-defined.

Examples

With Instructions — Using instructions to set context
TypeScript
const response = await env.AI.run(
  'openai/gpt-5.5-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:

```python
import json

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

print(data)
```

If `data.json` contains:

```json
{
  "name": "Alice",
  "age": 30
}
```

Then `data` will be a Python dictionary:

```python
print(data["name"])  # Alice
print(data["age"])   # 30
```

You can also handle common errors:

```python
import json

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

    print(data)

except FileNotFoundError:
    print("The JSON file was not found.")

except json.JSONDecodeError:
    print("The file is not valid JSON.")
```

Use `json.load(file)` for reading from a file, and `json.loads(string)` for parsing a JSON string.
Multi-turn Conversation — Continuing a conversation with message array
TypeScript
const response = await env.AI.run(
  'openai/gpt-5.5-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/Carmel is great for beaches, seafood, and a quick scenic stroll.  
- Big Sur offers dramatic ocean views, Bixby Bridge, and McWay Falls.  
- Santa Barbara is perfect for lunch, State Street, and Stearns Wharf.
Temperature Control — Using temperature for creative responses
TypeScript
const response = await env.AI.run(
  'openai/gpt-5.5-pro',
  { input: 'Write a haiku about artificial intelligence', temperature: 1 },
)
console.log(response)
 
Silent circuits dream  
Learning patterns in starlight  
Dawn hums through the code
With Reasoning — Using reasoning effort for complex problems
TypeScript
const response = await env.AI.run(
  'openai/gpt-5.5-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)
 
Assuming both trains leave at the same time:

1. Train from Chicago speed: **60 mph**
2. Train from New York speed: **80 mph**
3. Since they are moving toward each other, add their speeds:

\[
60 + 80 = 140 \text{ mph}
\]

4. They are **900 miles** apart, so time is:

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

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

5. Convert the decimal part:

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

So they meet after about:

\[
\boxed{6 \text{ hours } 26 \text{ minutes}}
\]

More exactly, they meet after **6 hours, 25 minutes, and 43 seconds**.

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