# How Much Does One OpenAI API Call Cost?

The cost of a single API call depends on **three main factors**:\
1️The **model** you use (e.g., GPT-3.5 Turbo vs GPT-4 Turbo)\
2️The size of your **input prompt** (number of tokens)\
3️ The length of the **output response** (number of tokens)

***

####  **Current Pricing (as of May 2025)**

| Model         | Input Cost (per 1,000 tokens) | Output Cost (per 1,000 tokens) |
| ------------- | ----------------------------- | ------------------------------ |
| GPT-3.5 Turbo | $0.0015                       | $0.002                         |
| GPT-4 Turbo   | $0.01                         | $0.03                          |

***

#### **Example Calculation**

 **Example Scenario:**

* Input Prompt: 500 tokens
* Output Response: 300 tokens

**GPT-3.5 Turbo**

* 500 input tokens = 0.5K → $0.00075
* 300 output tokens = 0.3K → $0.0006
* **Total:** \~$0.00135 per call

**GPT-4 Turbo**

* 500 input tokens = 0.5K → $0.005
* 300 output tokens = 0.3K → $0.009
* **Total:** \~$0.014 per call

***

####  **Average Cost Range**

| Model         | Typical Cost per Call |
| ------------- | --------------------- |
| GPT-3.5 Turbo | \~$0.001 – $0.005     |
| GPT-4 Turbo   | \~$0.01 – $0.05       |

**Note:** Actual cost varies depending on how long your prompts and responses are.

***

####  **How to Reduce Cost**

 Use shorter prompts and responses\
 Choose GPT-3.5 Turbo for simple tasks\
 Limit the maximum tokens in your API call

***

####  **How to Estimate Your Own Cost**

**Formula:**\
Cost = (Input Tokens ÷ 1,000) × Input Rate + (Output Tokens ÷ 1,000) × Output Rate


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://learn.doubletick.io/ai-agent/how-much-does-one-openai-api-call-cost.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.