# General

**URL:** https://community.perplexity.ai/c/general/4.md?page=4

[Latest](https://community.perplexity.ai/latest.md) · [Categories](https://community.perplexity.ai/categories.md) · [Tags](https://community.perplexity.ai/tags.md)

**Page:** 5

---

## [How do I create a new project?](https://community.perplexity.ai/t/how-do-i-create-a-new-project/531)

<div class="topic-metadata">

**Author:** [@juvjtwuus](https://community.perplexity.ai/u/juvjtwuus)\
**Replies:** 1\
**Last updated:** [June 11, 2025, 3:45pm UTC](https://community.perplexity.ai/t/how-do-i-create-a-new-project/531 "2025-06-11T15:45:55Z")

</div>

As you can see in the attached photo, the project isn’t being created, and I’m not sure why. I would really appreciate your help.

---

## [Support Public MCP Servers](https://community.perplexity.ai/t/support-public-mcp-servers/455)

<div class="topic-metadata">

**Author:** [@johannes\_agent\_ready](https://community.perplexity.ai/u/johannes_agent_ready)\
**Replies:** 2\
**Last updated:** [June 10, 2025, 8:52pm UTC](https://community.perplexity.ai/t/support-public-mcp-servers/455 "2025-06-10T20:52:43Z")

</div>

He!y We started a discussion around public MCP Servers on the OpenAI community forum and I’m curious what the Perplexity community’s thoughts are on this. Here’s the proposal: I would like to see Perplexity discover an…

---

## [Q: Showing Think results in sonar-pro and others via CURL API?](https://community.perplexity.ai/t/q-showing-think-results-in-sonar-pro-and-others-via-curl-api/162)

<div class="topic-metadata">

**Author:** [@yosun](https://community.perplexity.ai/u/yosun)\
**Replies:** 4\
**Last updated:** [May 26, 2025, 12:05pm UTC](https://community.perplexity.ai/t/q-showing-think-results-in-sonar-pro-and-others-via-curl-api/162 "2025-05-26T12:05:59Z")

</div>

Q: How do u show Think results in sonar-pro and others via CURL API structured outputs?

---

## [Is it okay to use text to image api for the project?](https://community.perplexity.ai/t/is-it-okay-to-use-text-to-image-api-for-the-project/203)

<div class="topic-metadata">

**Author:** [@Gurneesh\_Budhiraja](https://community.perplexity.ai/u/Gurneesh_Budhiraja)\
**Replies:** 1\
**Last updated:** [May 25, 2025, 9:57pm UTC](https://community.perplexity.ai/t/is-it-okay-to-use-text-to-image-api-for-the-project/203 "2025-05-25T21:57:24Z")

</div>

Hey this is regarding the Perplexity AI hackathon. Is it alright to use image generation models with the Perplexity API for the hackathon project?

---

## [Perplexity Hackathon Submission](https://community.perplexity.ai/t/perplexity-hackathon-submission/217)

<div class="topic-metadata">

**Author:** [@Bhavya\_Jain](https://community.perplexity.ai/u/Bhavya_Jain)\
**Replies:** 1\
**Last updated:** [May 25, 2025, 9:56pm UTC](https://community.perplexity.ai/t/perplexity-hackathon-submission/217 "2025-05-25T21:56:13Z")

</div>

For hackathon do we need to submit private repo url only? If our repo is public do we need to change visibility?

---

## [Submitting more than one project for the hackathon?](https://community.perplexity.ai/t/submitting-more-than-one-project-for-the-hackathon/156)

<div class="topic-metadata">

**Author:** [@Gurneesh\_Budhiraja](https://community.perplexity.ai/u/Gurneesh_Budhiraja)\
**Replies:** 2\
**Last updated:** [May 22, 2025, 12:39am UTC](https://community.perplexity.ai/t/submitting-more-than-one-project-for-the-hackathon/156 "2025-05-22T00:39:38Z")

</div>

Hi there, just want to know that is it alright to submit more than one project for the hackathon? Thanks

---

## [Request to add custom topics to the profile personalization option](https://community.perplexity.ai/t/request-to-add-custom-topics-to-the-profile-personalization-option/148)

<div class="topic-metadata">

**Author:** [@staceyodell](https://community.perplexity.ai/u/staceyodell)\
**Replies:** 1\
**Last updated:** [May 19, 2025, 7:22pm UTC](https://community.perplexity.ai/t/request-to-add-custom-topics-to-the-profile-personalization-option/148 "2025-05-19T19:22:43Z")

</div>

Is there a way you can add more drop down options for this? I would love to have things like data science python university or Arizona dachshunds etc. there is no option for them to be any different.

---

## [Extracting metadata from images using perplexity API?](https://community.perplexity.ai/t/extracting-metadata-from-images-using-perplexity-api/90)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:52pm UTC](https://community.perplexity.ai/t/extracting-metadata-from-images-using-perplexity-api/90 "2025-05-16T21:52:49Z")

</div>

Can we extract metadata from images using perplexity API?

---

## [Financial Data Hallucinations](https://community.perplexity.ai/t/financial-data-hallucinations/145)

<div class="topic-metadata">

**Author:** [@jamesliounis](https://community.perplexity.ai/u/jamesliounis)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:44pm UTC](https://community.perplexity.ai/t/financial-data-hallucinations/145 "2025-05-16T21:44:33Z")

</div>

:bug: Describe the Bug The Perplexity API on the sonar-reasoning-pro model is hallucinating the price of stock price. Returned Response: D-Wave Quantum Inc. (QBTS) Current Price: $4.20 Order Type: Limit Order Limit Pri…

---

## [Request regarding detailed costs for API use](https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:31pm UTC](https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96 "2025-05-16T21:31:29Z")

</div>

Hi to all, doing great job with the API!!! I now want to clarify the actual exact cost structure, because I want to implement this in my script. I have seen the following: Model Price per 1000 requests Price per 1…

---

## [\<API model mismatch – sonar-deep-research returns sonar-reasoning-pro\>](https://community.perplexity.ai/t/api-model-mismatch-sonar-deep-research-returns-sonar-reasoning-pro/144)

<div class="topic-metadata">

**Author:** [@jamesliounis](https://community.perplexity.ai/u/jamesliounis)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:27pm UTC](https://community.perplexity.ai/t/api-model-mismatch-sonar-deep-research-returns-sonar-reasoning-pro/144 "2025-05-16T21:27:56Z")

</div>

:bug: Describe the Bug We’re making API calls to the Sonar Deep Research model, but the responses we receive come from Sonar Reasoning Pro. Additionally, the dashboard shows usage of Reasoning Pro and we’re being billed …

---

## [Bad requests leak verbose logs](https://community.perplexity.ai/t/bad-requests-leak-verbose-logs/108)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:19pm UTC](https://community.perplexity.ai/t/bad-requests-leak-verbose-logs/108 "2025-05-16T21:19:30Z")

</div>

I just want to flag that certain malformed requests leak error messages that show more information about the API than they should. Nothing serious but I wanted to flag. { "model": "sonar-pro", "messages": \[ { …

---

## [Why can't use OpenAI, Claude Model, Languages other than English have serious performance issues](https://community.perplexity.ai/t/why-cant-use-openai-claude-model-languages-other-than-english-have-serious-performance-issues/69)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 16, 2025, 9:14pm UTC](https://community.perplexity.ai/t/why-cant-use-openai-claude-model-languages-other-than-english-have-serious-performance-issues/69 "2025-05-16T21:14:42Z")

</div>

I am a user using the API, but in the case of languages ​​other than English, the performance is so poor that I cannot use it with the currently available model. Can you make it possible to utilize the OpenAI and Claude…

---

## [Supported Models Link in Docs Redirects to Home](https://community.perplexity.ai/t/supported-models-link-in-docs-redirects-to-home/105)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/supported-models-link-in-docs-redirects-to-home/105 "2025-05-15T00:16:37Z")

</div>

Hi Y’all! The new docs don’t seem to list support models anymore. Specifically, Home - Perplexity redirects to Home - Perplexity. This is the address referenced in the below image. Are the supported models listed elsewh…

---

## [Bug: Chat completions endpoint implements SSE via POST instead of GET](https://community.perplexity.ai/t/bug-chat-completions-endpoint-implements-sse-via-post-instead-of-get/93)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 0\
**Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/bug-chat-completions-endpoint-implements-sse-via-post-instead-of-get/93 "2025-05-15T00:15:34Z")

</div>

I was running into a “method not allowed” when using stream and upon inspection I realised the API does not adhere to what I thought was the SSE spec by using a “POST” method for the server-sent events endpoint mode. Now…

---

## [Mixed Results with Perplexity API](https://community.perplexity.ai/t/mixed-results-with-perplexity-api/81)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:14am UTC](https://community.perplexity.ai/t/mixed-results-with-perplexity-api/81 "2025-05-15T00:14:16Z")

</div>

So overall I’m happy with the API. As far as I know it’s the only one that is actually returning web results. I do not believe that this is a feature as of yet with ChatGPT or Gemini. What I’ve found is an extreme inc…

---

## [Beta features access](https://community.perplexity.ai/t/beta-features-access/78)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 0\
**Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/beta-features-access/78 "2025-05-15T00:13:58Z")

</div>

Hello, Over the past six months, I have applied multiple times to the closed beta to gain access to the domain filter but have not received any response yet. Could you please provide more information about this process…

---

## [Sources for perplexity](https://community.perplexity.ai/t/sources-for-perplexity/67)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 3\
**Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/sources-for-perplexity/67 "2025-05-15T00:12:45Z")

</div>

wondering when it will be out of beta?

---

## [Why are citations hidden behind the closed beta version of the API?](https://community.perplexity.ai/t/why-are-citations-hidden-behind-the-closed-beta-version-of-the-api/66)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 3\
**Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/why-are-citations-hidden-behind-the-closed-beta-version-of-the-api/66 "2025-05-15T00:12:32Z")

</div>

If the whole point of this tool is to provide accurate answers searched online, why are the citations not available, and that I have to request for it to be enabled via the closed beta form?

---

## [Login required after 3 questions (in Browser)? No chat without account?](https://community.perplexity.ai/t/login-required-after-3-questions-in-browser-no-chat-without-account/65)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/login-required-after-3-questions-in-browser-no-chat-without-account/65 "2025-05-15T00:12:21Z")

</div>

As I found out I am always prompted for a login after 3 questions to Perplexity in browser. So there is no workaround to evaluate Perplexity with account?

---

## [Many HTTP status code 524 errors for API responses](https://community.perplexity.ai/t/many-http-status-code-524-errors-for-api-responses/63)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/many-http-status-code-524-errors-for-api-responses/63 "2025-05-15T00:12:10Z")

</div>

Hi, We’re facing many HTTP status code 524 errors of responses for API requests while rate limits are not hit obviously. Does anyone know if there is additional rate limit other than what is listed here Rate Limits - P…

---

## [Strange instances of hallucinations where "Initialized" and "assistant" were inserted into Perplexity API responses](https://community.perplexity.ai/t/strange-instances-of-hallucinations-where-initialized-and-assistant-were-inserted-into-perplexity-api-responses/62)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 0\
**Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/strange-instances-of-hallucinations-where-initialized-and-assistant-were-inserted-into-perplexity-api-responses/62 "2025-05-15T00:12:04Z")

</div>

I’ve seen 3 instances recently where these words strangely seemed to leak into the output of the Perplexity API - 2 instances with Initialized and 1 instance of assistant. In each case the prompt was a yes/no question an…

---

## [API token usage reports and billing](https://community.perplexity.ai/t/api-token-usage-reports-and-billing/60)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/api-token-usage-reports-and-billing/60 "2025-05-15T00:11:53Z")

</div>

I’m testing the API. With minimal usage, the billing seems to be deducting excessively more than expected from my purchased credits. Is there a way to see how many API tokens I am using?

---

## [Subpar responses when using pplx api when compared to perplexity labs](https://community.perplexity.ai/t/subpar-responses-when-using-pplx-api-when-compared-to-perplexity-labs/58)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 2\
**Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/subpar-responses-when-using-pplx-api-when-compared-to-perplexity-labs/58 "2025-05-15T00:11:40Z")

</div>

I tried a few questions which needed knowledge of recent events (2-3 months back), and the api response claims to have never head of it while in labs I get the desired response everytime. I tried both sonar large online …

---

## [Bare minimum example on website is wrong](https://community.perplexity.ai/t/bare-minimum-example-on-website-is-wrong/56)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 2\
**Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/bare-minimum-example-on-website-is-wrong/56 "2025-05-15T00:11:25Z")

</div>

Hi, The bare minimum example of querying the API via Python is not correct. If you try the code below it will fail with an 401 Authorization error: from openai import OpenAI YOUR\_API\_KEY = "INSERT API KEY HERE" mess…

---

## [API very slow / returning 5xx errors](https://community.perplexity.ai/t/api-very-slow-returning-5xx-errors/55)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 2\
**Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/api-very-slow-returning-5xx-errors/55 "2025-05-15T00:11:16Z")

</div>

hi there, I am testing the perplexity API to see if I can use it in a new app. It is taking around 47 seconds to return a response. Out of my last 6 tests I got 3 5xx errors and 3 200s. is it normal to get that many…

---

## [Why is the model not using online search?](https://community.perplexity.ai/t/why-is-the-model-not-using-online-search/52)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 2\
**Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/why-is-the-model-not-using-online-search/52 "2025-05-15T00:10:51Z")

</div>

The model has been working perfectly fine before today morning, intermittently it will work and use live data from the web in it’s search, but over 60% of my api calls this morning have gotten the response that it doesn’…

---

## [Perplexity Pro Bonus for the API is set to zero](https://community.perplexity.ai/t/perplexity-pro-bonus-for-the-api-is-set-to-zero/51)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/perplexity-pro-bonus-for-the-api-is-set-to-zero/51 "2025-05-15T00:10:42Z")

</div>

I paid for the Pro subscription but I did not receive the 5 dollars to use the API. Did I miss something or is there a problem?

---

## [Why is the rate limit so low?](https://community.perplexity.ai/t/why-is-the-rate-limit-so-low/47)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/why-is-the-rate-limit-so-low/47 "2025-05-15T00:10:14Z")

</div>

Basically the title. The limit for Chat models is 20/min. What type of applications can developers build with that limit?

---

## [API seems to not be working very well](https://community.perplexity.ai/t/api-seems-to-not-be-working-very-well/46)

<div class="topic-metadata">

**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Replies:** 1\
**Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/api-seems-to-not-be-working-very-well/46 "2025-05-15T00:10:08Z")

</div>

Currently trying to do some experimental work with the API. It was returning some reasonably good results but for a while now it’s been throwing a lot of 500 errors. Moreover, I recently got a full blown HTML error respo…

[Previous page](https://community.perplexity.ai/c/general/4.md?page=3)

[Next page](https://community.perplexity.ai/c/general/4.md?page=5)
