Tokens

Tokens are small text units — words or parts of words — used by the model to process and generate language.

Pricing

Source: https://platform.openai.com/docs/pricing?latest-pricing=standard 
Below is the current pricing for GPT-5 models (per 1 million tokens):
 

*(per 1 million tokens)*

Example for gpt-5-nano:

         Input:           "Write a short poem about the ocean."               (Estimated 8 tokens)
         Output:   "The ocean whispers softly under the moonlight."      (Estimated 10 tokens)
 

     Input:      8 tokens × $0.05 / 1,000,000 = $0.0000004
Output:    10 tokens × $0.40 / 1,000,000 = $0.000004

Total cost ≈ $0.0000044

 Installation

pip install openai

OpenAI account & Payment

• Create an account on the OpenAI platform: https://platform.openai.com/docs/overview
• Click the settings (cogwheel) icon in the top-right corner.
• In the side menu click:  Billing 
• Add funds to your account using   Add to credit balance 

API Key

• Click the settings (cogwheel) icon in the top-right corner.
• In the side menu click:  Billing 
•   + Create new secret key 
• Optionally give a name to they key
• Select a Project. If you didn't create any, choose Default Project
• Save your key 

Example

from openai import OpenAI

client = OpenAI(api_key="****")

response = client.chat.completions.create(
    model="gpt-5-nano",
    messages=[
        {"role": "user", "content": "Write a short poem about the ocean."}
    ]
)

print(response.choices[0].message.content)

model → defines which model will be used.
Available models: https://platform.openai.com/docs/models

messages → list of messages that make up the chat.
Each message has a role and a content.

role → indicates who is sending the text:

• "user" — represents what the user writes.
   

content → the actual text of the message.

response.choices[0].message.content → contains the model’s generated reply.