Frequently Asked Questions

Will user data submitted through the API be used for model training or other purposes?

We collect the following types of information:

API Usage Data: We collect information about your use of our API, such as the number of requests, the content of the requests, and the timestamps of the requests.

User Account Information: When you create an account with us, we collect your name, email address, and other relevant contact information.

We do not utilize the data provided to and generated by our API for the purpose of training Perplexity models or enhancing Perplexity's services. However, if you wish to contribute to the ongoing improvement of our models, you can complete this form to voluntarily share your data with us.

Does the pplx-api currently support web browsing?

No, but we are planning on releasing a RAG-LLM in the near future. Reach out to [email protected] for business inquiries.

What is the commercial pricing?

We will release a commercial pricing in the near future. Reach out to [email protected] for business inquiries.

Can I use pplx-api commercially?

Reach out to [email protected] for business inquiries.

What are the limitations to the number of API calls?

You can find our rate limits here.

Are there any other open source models you plan on offering in the future?

We are committed to adding high performant open-source models as they become available. This includes future open-sourced Llama and Mistral models.

What's the best way to stay up to date with API updates?

Please join our API channel on Discord.

Is there any way to get a token rate limit increase?

Please reach out to [email protected] if you require a rate limit increase for commercial purposes. We consider rate limit increases on a case by case basis.

Do you support fine-tuning?

Currently, we do not support fine-tuning. Please reach out to [email protected] if you are interested in this.

Does pplx-api support custom base models?

Currently, we do not support custom base models. Please reach out to [email protected] if you are interested in this.

There's a model I would like to use that isn't available on pplx-api.

Please reach out to [email protected] if you would like to request a new model.

I have another question or an issue.

Please reach out to [email protected] for commercial or business inquiries. Please join our Discord channel for bug reports, questions, or general feedback.

Does Perplexity provide service quality assurances such as service uptime, frequency of failures, and target recovery time in the event of a failure?

We do not guarantee this at the moment.