It looks like the trending need to use AI in software is just growing with big temp. One of the innovators in the field is OpenAI with its product ChatGPT. The way to integrate with ChatGPT is through the API key.
This post will look at different aspects of Chat GPT API.
Table of contents
What is Chat GPT API?
The ChatGPT API is a product of OpenAI that enables developers to access the capabilities of the GPT model.
Specifically designed for natural language processing and text generation.
It allows the integration of AI-driven language generation into various applications, services, or platforms.
How to Get Chat GPT API Key?
- You will need to create an OpenAI account, which is straightforward.
- After you have created an account and logged in successfully, from the sidebar menu select API keys.
This is the place to manage your Chat GPT API keys.
Important:
- API keys can only be copied at the time of creation
- API keys are secret and you should NOT be shown publicly
For flexibility, you can assign organization to your key.
Organizations can be managed from Settings -> Organization
Related article: Top 7 Chat GPT Alternatives That Will Increase Your Productivity
How Much Does Chat GPT API Cost?
Chat GPT API is NOT free. You can find the up-to-date pricing here.
Using OpenAI API you will pay only for what you have used.
OpenAI offers different models, everyone with different capabilities and prices.
Language models are:
- GPT-4 Turbo
- GPT-4
- GPT-3.5 Turbo
- Assistants API
- Fine-tuning models
- Embedding models
- Base models
For language models, prices are for every 1000 tokens, which you can consider as parts of words. About 1000 tokens make up roughly 750 words.
You can calculate the tokens of your text in the Tokenizer.
There are Other models which include Image models, Audio models, and Older models.
Related article: Who Owns Chat GPT And OpenAI? The Story Of AI Success!
GPT-4 Turbo
GPT-4 Turbo is stronger than GPT-4, has more recent information, and can handle bigger tasks. Plus, it costs less.
| Model | Input | Output |
| gpt-4-1106-preview | $0.01 / 1K tokens | $0.03 / 1K tokens |
| gpt-4-1106-vision-preview | $0.01 / 1K tokens | $0.03 / 1K tokens |
GPT-4
GPT-4 knows a lot about many different things and is really good at understanding complicated instructions in regular language. It can handle difficult tasks accurately.
| Model | Input | Output |
| gpt-4 | $0.03 / 1K tokens | $0.06 / 1K tokens |
| gpt-4-32k | $0.06 / 1K tokens | $0.12 / 1K tokens |
GPT-3.5 Turbo
GPT-3.5 Turbo models are both good at what they do and affordable.
The main one, gpt-3.5-turbo, is the best in this group, can handle up to 16K information at once, and works best for conversations.
Then there’s gpt-3.5-turbo-instruct, a different type meant for following instructions, but it can only handle up to 4K information at a time.
| Model | Input | Output |
| gpt-3.5-turbo-1106 | $0.0010 / 1K tokens | $0.0020 / 1K tokens |
| gpt-3.5-turbo-instruct | $0.0015 / 1K tokens | $0.0020 / 1K tokens |
Related article: ChatGPT Jailbreak Prompts Ultimate Guide 2023
Assistants API
The Assistants API and tools, like the retrieval and code interpreter, help developers create AI assistants for their apps. Each assistant has its own fee based on the storage of files it uses. The retrieval tool organizes and saves your files’ information in our database.
When you use the Assistant API, you’re charged based on the number of tokens used in the chosen language model’s input/output rates. The assistant smartly picks which part of the conversation to include when using the model.
More info about assistants API
| Tool | Input |
| Code interpreter | $0.03 / session (free until 12/1/2023) |
| Retrieval | $0.20 / GB / assistant / day (free until 12/13/2023) |
Fine-tuning models
You can make your own special models by adjusting our basic models with your own training information. After you’ve made these adjustments, you’ll only pay for the tokens you use when you make requests to that particular model.
More info about fine-tuning models
| Model | Training | Input usage | Output usage |
| gpt-3.5-turbo | $0.0080 / 1K tokens | $0.0030 / 1K tokens | $0.0060 / 1K tokens |
| davinci-002 | $0.0060 / 1K tokens | $0.0120 / 1K tokens | $0.0120 / 1K tokens |
| babbage-002 | $0.0004 / 1K tokens | $0.0016 / 1K tokens | $0.0016 / 1K tokens |
Embedding models
Use our embedding service to create powerful searches, group similar items together, find main topics, and categorize things easily.
More info about embedding models
| Model | Usage |
| ada v2 | $0.0001 / 1K tokens |
Base models
The basic GPT models aren’t great at following instructions and have fewer abilities. However, they can become better at specific jobs if you adjust them to focus on those particular tasks.
| Model | Usage |
| davinci-002 | $0.0020 / 1K tokens |
| babbage-002 | $0.0004 / 1K tokens |
Image models
Include DALL·E in your apps to create and change unique images and art. DALL·E 3 is the best quality model, while DALL·E 2 is made to be more affordable.
| Model | Quality | Resolution | Price |
| DALL·E 3 | Standard | 1024×1024 | $0.040 / image |
| Standard | 1024×1792, 1792×1024 | $0.080 / image | |
| DALL·E 3 | HD | 1024×1024 | $0.080 / image |
| HD | 1024×1792, 1792×1024 | $0.120 / image | |
| DALL·E 2 | 1024×1024 | $0.020 / image | |
| 512×512 | $0.018 / image | ||
| 256×256 | $0.016 / image |
Audio models
Using audio models you can convert text to speech or speech to text.
| Model | Usage |
| Whisper | $0.006 / minute (rounded to the nearest second) |
| TTS | $0.015 / 1K characters |
| TTS HD | $0.030 / 1K characters |
Older models (Deprecations)
Information about older models can be found here
Frequently Asked Question
Tokens are like small parts of words that computers use to understand language. In English text, one token is around 4 letters or 0.75 words.
Yes, ChatGPT has an API that gives users the ability to use its language generation capabilities. This API allows developers to integrate ChatGPT into their applications and systems.
No, the ChatGPT API is not free. It is a paid service that charges per token. The pricing varies by model, but it is typically around $0.002 per token. To use the ChatGPT API, you will need to create an account on OpenAI and sign up for a pricing plan.
The ChatGPT API costs $0.002 per 1000 tokens. This means that it costs $0.002 to generate 750 words of text.
No, the OpenAI API is not entirely free, but it does offer a free trial with free credits.
What Does GPT Stand For In Chat GPT? Explained!