# Hot **URL:** https://community.perplexity.ai/hot.md?page=7 [Latest](https://community.perplexity.ai/latest.md) · [Categories](https://community.perplexity.ai/categories.md) · [Tags](https://community.perplexity.ai/tags.md) **Page:** 8 --- ## [Citations which are not useful/relevant to the query](https://community.perplexity.ai/t/citations-which-are-not-useful-relevant-to-the-query/88)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:14am UTC](https://community.perplexity.ai/t/citations-which-are-not-useful-relevant-to-the-query/88 "2025-05-15T00:14:59Z")
The field response.choices\[0\].message.content returned a text that says that only two links were found relevant but the citations array contained 5 links. Indeed only the first two were relevant, and I have no clue how … --- ## [Can i use the upload files option through the perplexity API?](https://community.perplexity.ai/t/can-i-use-the-upload-files-option-through-the-perplexity-api/92)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/can-i-use-the-upload-files-option-through-the-perplexity-api/92 "2025-05-15T00:15:29Z")
So the thing is my usecase involves uploading files that are over 128k tokens, so i need to upload them as files. It works through the interface but i didnt find any relevant docs related to it can you provide me with th… --- ## [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)
**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")
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… --- ## [Clarification on Perplexity API: Does it Provide Access to Search Functionality or Only AI Models?](https://community.perplexity.ai/t/clarification-on-perplexity-api-does-it-provide-access-to-search-functionality-or-only-ai-models/94)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/clarification-on-perplexity-api-does-it-provide-access-to-search-functionality-or-only-ai-models/94 "2025-05-15T00:15:38Z")
Hello, I’m currently exploring the Perplexity API for a project and have encountered a key difference between the API responses and the real-time data I receive from the Perplexity web client. While the web client appe… --- ## [How would I disable online search on the ppl API?](https://community.perplexity.ai/t/how-would-i-disable-online-search-on-the-ppl-api/95)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/how-would-i-disable-online-search-on-the-ppl-api/95 "2025-05-15T00:15:42Z")
What would I need to do to disable the online search of the ppl API? I would like to use only the text I provide it with. --- ## [Citation references are sometimes corrupted](https://community.perplexity.ai/t/citation-references-are-sometimes-corrupted/97)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/citation-references-are-sometimes-corrupted/97 "2025-05-15T00:15:51Z")
We’re using the streaming mode to interact with the API. Sometimes we see corrupted citation references in the text. In the following screenshot the \[3\] reference is corrupted and transferred as \[3/\>. When it happens… --- ## [How to make the neural network learn from its mistakes](https://community.perplexity.ai/t/how-to-make-the-neural-network-learn-from-its-mistakes/98)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/how-to-make-the-neural-network-learn-from-its-mistakes/98 "2025-05-15T00:15:55Z")
Hello. What do I need to do to make the neural network learn from its mistakes via API and become better and better by analyzing the responses it receives? --- ## [Determines whether or not a request to an online model should return images. Images are in closed beta](https://community.perplexity.ai/t/determines-whether-or-not-a-request-to-an-online-model-should-return-images-images-are-in-closed-beta/99)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/determines-whether-or-not-a-request-to-an-online-model-should-return-images-images-are-in-closed-beta/99 "2025-05-15T00:15:59Z")
Hello! When will this feature be passed to LTS? --- ## [Sonar Huge Consistently Stalling While Writing Answers in Firefox](https://community.perplexity.ai/t/sonar-huge-consistently-stalling-while-writing-answers-in-firefox/100)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/sonar-huge-consistently-stalling-while-writing-answers-in-firefox/100 "2025-05-15T00:16:06Z")
See subject. I use Perplexity as my default search engine in Firefox 134 on Windows 11, but this also happens when I run a query directly on the Perplexity.ai website. I tried clearing my browser cache and cookies and re… --- ## [Is there no batch api?](https://community.perplexity.ai/t/is-there-no-batch-api/101)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/is-there-no-batch-api/101 "2025-05-15T00:16:12Z")
I am currently using OpenAI’s batch API, to run requests in bulk when they are not urgent. Also for the cost advantage Is there a similar functionality in perplexity? And if not, is it planned for near future? --- ## [Getting error back from API Key. I will attach my code below. I'm also not seeing any console log messages, and my failed attempts are charging me a few cents. Need advice](https://community.perplexity.ai/t/getting-error-back-from-api-key-i-will-attach-my-code-below-im-also-not-seeing-any-console-log-messages-and-my-failed-attempts-are-charging-me-a-few-cents-need-advice/102)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/getting-error-back-from-api-key-i-will-attach-my-code-below-im-also-not-seeing-any-console-log-messages-and-my-failed-attempts-are-charging-me-a-few-cents-need-advice/102 "2025-05-15T00:16:19Z")
Here is my code. I am unable to see any console log messages, yet a file is being produced and charging me a few cents. Trying to iterate a prompt over a file with 300 rows, testing it on just 2 rows for now. Working on … --- ## [Uploading documents](https://community.perplexity.ai/t/uploading-documents/103)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/uploading-documents/103 "2025-05-15T00:16:24Z")
I was wondering whether there’s a similar feature as we have in the UI where we can upload a file that is used with chat-interactions. The use case here would be that we can i.e. upload the documentation of a website lik… --- ## [Seeking alternatives for llama-3.1-sonar-large-128k-online after February 22, 2025](https://community.perplexity.ai/t/seeking-alternatives-for-llama-3-1-sonar-large-128k-online-after-february-22-2025/104)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/seeking-alternatives-for-llama-3-1-sonar-large-128k-online-after-february-22-2025/104 "2025-05-15T00:16:30Z")
Hello everyone, I’ve recently learned that the llama-3.1-sonar-large-128k-online model will be discontinued on February 22, 2025(Home - Perplexity). As a frequent user of this model, I’m looking for advice on potential … --- ## [Supported Models Link in Docs Redirects to Home](https://community.perplexity.ai/t/supported-models-link-in-docs-redirects-to-home/105)
**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")
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… --- ## [Search\_domain\_filter, sub-domain and increase limit](https://community.perplexity.ai/t/search-domain-filter-sub-domain-and-increase-limit/106)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 3\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/search-domain-filter-sub-domain-and-increase-limit/106 "2025-05-15T00:16:48Z")
Today, the current solution is limited to only 3 domains for whitelisting and blacklisting. It would be great if this limit could be increased to 10. In line with increasing the limit, it would be useful to be able to … --- ## [When Carbon features will be incorporated to Perplexity?](https://community.perplexity.ai/t/when-carbon-features-will-be-incorporated-to-perplexity/107)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:16am UTC](https://community.perplexity.ai/t/when-carbon-features-will-be-incorporated-to-perplexity/107 "2025-05-15T00:16:52Z")
Hi Perplexity Team! Where can I find information about when Carbon features will be incorporated into Perplexity (Standard, Enterprise, API) as well as a description of the features and the way they will work with Perpl… --- ## [After updating: Network timeout at: https://api.perplexity.ai/chat/completions](https://community.perplexity.ai/t/after-updating-network-timeout-at-https-api-perplexity-ai-chat-completions/109)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 4\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/after-updating-network-timeout-at-https-api-perplexity-ai-chat-completions/109 "2025-05-15T00:17:09Z")
I have updated my code for the new model: { "model": "sonar", "messages": \[ { "role": "system", "content": "Be precise and concise." }, { "role": "user", "content": "Private Promp… --- ## [Return\_images and return\_related\_questions seem to be supported in general API now, but nothing returned](https://community.perplexity.ai/t/return-images-and-return-related-questions-seem-to-be-supported-in-general-api-now-but-nothing-returned/111)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/return-images-and-return-related-questions-seem-to-be-supported-in-general-api-now-but-nothing-returned/111 "2025-05-15T00:17:20Z")
Am I missing something? There’s nothing in the API describing how image and related question results are formatted and nothing seems to be returned. --- ## [How can I use new model: soner-pro through MCP with Claude?](https://community.perplexity.ai/t/how-can-i-use-new-model-soner-pro-through-mcp-with-claude/112)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/how-can-i-use-new-model-soner-pro-through-mcp-with-claude/112 "2025-05-15T00:17:24Z")
Hi all, I’ve been notified that there’s coming a new AI model and accordingly new documentations. I have updated my API key. My MCP config setting doesn’t have model description so that Perplexity still uses llama after … --- ## [Search\_domain\_filter issues](https://community.perplexity.ai/t/search-domain-filter-issues/113)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/search-domain-filter-issues/113 "2025-05-15T00:17:31Z")
saw a q about this arg not working below, but want to flush it out. seeing: TypeError: create() got an unexpected keyword argument ‘search\_domain\_filter’ when using: response = client.chat.completions.create( mode… --- ## [Request for small sonar model](https://community.perplexity.ai/t/request-for-small-sonar-model/114)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 2\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-for-small-sonar-model/114 "2025-05-15T00:17:40Z")
We’re currently using the llama-3.1-sonar-small-128k-online model, which is set to be deprecated on 2025-02-22. We’re moving over to the new sonar model but noticing it is significantly slower than the legacy small model… --- ## [\[Request\] Improve Documentation of Usage Tiers to Address User Confusion](https://community.perplexity.ai/t/request-improve-documentation-of-usage-tiers-to-address-user-confusion/115)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 2\ **Last updated:** [May 15, 2025, 12:17am UTC](https://community.perplexity.ai/t/request-improve-documentation-of-usage-tiers-to-address-user-confusion/115 "2025-05-15T00:17:48Z")
Request I’d like to formally ask the maintainers (@shubhang98) to address the unclear documentation of the new Usage Tiers feature introduced with the Sonar and Sonar-Pro models. Issue Usage Tiers were added to the Perp… --- ## [Why don't I receive the same level of response using the API as I do using the official UI search?](https://community.perplexity.ai/t/why-dont-i-receive-the-same-level-of-response-using-the-api-as-i-do-using-the-official-ui-search/116)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 9\ **Last updated:** [May 15, 2025, 12:22am UTC](https://community.perplexity.ai/t/why-dont-i-receive-the-same-level-of-response-using-the-api-as-i-do-using-the-official-ui-search/116 "2025-05-15T00:22:44Z")
Hello, I’m starting to use the Perplexity API to integrate information query functionalities into an ERP. As I’m just beginning, I suspect I might be doing something wrong. The issue is that a simple question like “Is t… --- ## [Is sonar-reasoning the same as deepseek-reasoner?](https://community.perplexity.ai/t/is-sonar-reasoning-the-same-as-deepseek-reasoner/117)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:22am UTC](https://community.perplexity.ai/t/is-sonar-reasoning-the-same-as-deepseek-reasoner/117 "2025-05-15T00:22:49Z")
I would like more information about your model offerings in your API. Is sonar-reasoning based on deepseek-reasoner? If it isn’t a verbatim instance, what has been changed? --- ## [Sonar-pro API problem](https://community.perplexity.ai/t/sonar-pro-api-problem/118)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:22am UTC](https://community.perplexity.ai/t/sonar-pro-api-problem/118 "2025-05-15T00:22:53Z")
When using the sonar-pro API, the cost is charged even though there is no result. --- ## [Perplexity Search output is getting worse compared to ChatGPT on Non-Technical Creating Documents or Templates related output](https://community.perplexity.ai/t/perplexity-search-output-is-getting-worse-compared-to-chatgpt-on-non-technical-creating-documents-or-templates-related-output/120)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:23am UTC](https://community.perplexity.ai/t/perplexity-search-output-is-getting-worse-compared-to-chatgpt-on-non-technical-creating-documents-or-templates-related-output/120 "2025-05-15T00:23:02Z")
Perplexity Search output is getting worse compared to ChatGPT on Non-Technical Creating Documents or Templates related output --- ## [The API returns Citations not as a separate independent field, but in the body of the Content field. What's the problem?](https://community.perplexity.ai/t/the-api-returns-citations-not-as-a-separate-independent-field-but-in-the-body-of-the-content-field-whats-the-problem/121)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:23am UTC](https://community.perplexity.ai/t/the-api-returns-citations-not-as-a-separate-independent-field-but-in-the-body-of-the-content-field-whats-the-problem/121 "2025-05-15T00:23:06Z")
Previously, everything worked as in API Reference " “id”: “3c90c3cc-0d44-4b50-8888-8dd25736052a”, “model”: “sonar”, “object”: “chat.completion”, “created”: 1724369245, “citations”: \[ “Astro for kids: How many star… --- ## [Where can i find the price of perplexity API CHAT models (not online)?](https://community.perplexity.ai/t/where-can-i-find-the-price-of-perplexity-api-chat-models-not-online/122)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:23am UTC](https://community.perplexity.ai/t/where-can-i-find-the-price-of-perplexity-api-chat-models-not-online/122 "2025-05-15T00:23:13Z")
I am still using llama 70b chat via perplexyty API because of the free included api credits in the perplexity subscription. But 1 euro per million tokens seems overpriced nowadays for this model. But I cannot find a new … --- ## [Not being able to generate images, I am pro user but I am not able to generate images ? can someone guide me?](https://community.perplexity.ai/t/not-being-able-to-generate-images-i-am-pro-user-but-i-am-not-able-to-generate-images-can-someone-guide-me/123)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:26am UTC](https://community.perplexity.ai/t/not-being-able-to-generate-images-i-am-pro-user-but-i-am-not-able-to-generate-images-can-someone-guide-me/123 "2025-05-15T00:26:39Z")
import requests import json import random from datetime import datetime def generate\_facebook\_post(api\_key, topic=“positivity”): “”“Generates post content and image using Perplexity AI”“” try: # Generate text post … --- ## [Modify/Select sources to answer from](https://community.perplexity.ai/t/modify-select-sources-to-answer-from/124)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 2\ **Last updated:** [May 15, 2025, 12:26am UTC](https://community.perplexity.ai/t/modify-select-sources-to-answer-from/124 "2025-05-15T00:26:48Z")
Is there a way for selecting the sources. I am building a business specific chatbot using perplexity-api, but the sources are too generic. How can I get sources which are authentic/reputable For example: If I ask a que… [Previous page](https://community.perplexity.ai/hot.md?page=6) [Next page](https://community.perplexity.ai/hot.md?page=8)