We generally recommend that developers use either gpt-4 or gpt-3.5-turbo, depending on how complex the tasks you are using the models for are. gpt-4 generally performs better on a wide range of evaluations, while gpt-3.5-turbo returns outputs with lower latency and costs much less per token. We recommend experimenting with these models in Playground to investigate which models provide the best price performance trade-off for your usage. A common design pattern is to use several distinct query types which are each dispatched to the model appropriate to handle them.

Log in to your account to view your usage tracking dashboard. This page will show you how many tokens you’ve used during the current and past billing cycles.

You can set a monthly budget in your billing settings, after which we’ll stop serving your requests. There may be a delay in enforcing the limit, and you are responsible for any overage incurred. You can also configure an email notification threshold to receive an email alert once you cross that threshold each month. We recommend checking your usage tracking dashboard regularly to monitor your spend.

No, the ChatGPT API and ChatGPT Plus subscription are billed separately. The API has its own pricing, which can be found at https://openai.com/pricing. The ChatGPT Plus subscription covers usage on chat.openai.com only and costs $20/month.

Yes, we treat Playground usage the same as regular API usage.

Chat completion requests are billed based on the number of input tokens sent plus the number of tokens in the output(s) returned by the API.

Your request may use up to num_tokens(input) + [max_tokens * max(n, best_of)] tokens, which will be billed at the per-engine rates outlined at the top of this page.

In the simplest case, if your prompt contains 200 tokens and you request a single 900 token completion from the gpt-3.5-turbo-1106 API, your request will use 1100 tokens and will cost [(200 * 0.001) + (900 * 0.002)] / 1000 = $0.002.

You can limit costs by reducing prompt length or maximum response length, limiting usage of best_of/n , adding appropriate stop sequences, or using engines with lower per-token costs.

There are two components to fine-tuning pricing: training and usage.

When training a fine-tuned model, the total tokens used will be billed according to our training rates. Note that the number of training tokens depends on the number of tokens in your training dataset and your chosen number of training epochs. The default number of epochs is 4.

Once you fine-tune a model, you’ll be billed only for the tokens you use. Requests sent to fine-tuned models are billed at our usage rates.

We will be publishing an SLA soon. In the meantime you can visit our Status page to monitor service availability and view historical uptime. If your company or application has specific requirements, please contact our sales team.

Yes. Azure customers can access the OpenAI API on Azure with the compliance, regional support, and enterprise-grade security that Azure offers. Learn more or contact sales@openai.com.