OpenAI API Pricing calculator

The table below provides a pricing calculator for OpenAI GPT API, Azure OpenAI APIs, Google Palm API and Anthropic Claude API. Select the model you want:

An execution includes both the prompt sent and the response.
Language: English

The language defines the way the words are divided into tokens, and therefore has an impact on the price.

English: 1 word ≈ 1.3 tokens
Spanish: 1 word ≈ 2 tokens
French: 1 word ≈ 2 tokens

Tokens per executionWords per executionPrice for 1 execution

This model has a different rate for prompt and completion. This price is computed with prompt tokens = completion tokens.

Price forexecutions

This model has a different rate for prompt and completion. This price is computed with prompt tokens = completion tokens.

108~$0.00002~$0.02
2015~$0.00003~$0.03
5038~$0.00009~$0.09
10075~$0.00017~$0.17
200150~$0.00035~$0.35
500375~$0.00088~$0.88
1000750~$0.00175~$1.75
20001500~$0.00350~$3.50
40003000~$0.00700~$7.00

FAQ

What is an OpenAI token?

A token is the unit of account of OpenAI. Read our guide on tokens here.

What is an OpenAI execution?

An OpenAI execution is the combination of the invite to OpenAI and the response from OpenAI.
All words in the prompt and response count for billing.

What is an OpenAI prompt?

The prompt is the instructions or question you send to OpenAI in order to get a response. It is text written in normal, natural language, for example:
Prompt: "Write a tagline for an ice cream shop".

What is an OpenAI response?

This is the response OpenAI gives you to the prompt you sent, for example:
Prompt: "Write a tagline for an ice cream shop"
Response: “We serve up smiles with every scoop!”

Can I set an OpenAI billing limit?

You can configure a billing limit in the OpenAI billing settings, in order to control your costs.

How to monitor my OpenAI API usage and cost?

You can review your usage in the OpenAI dashboard usage section.
You can easily set a spending limit in the OpenAI dashboard billing section.