# Latest **URL:** https://community.perplexity.ai/latest.md?page=15 [Latest](https://community.perplexity.ai/latest.md) · [Categories](https://community.perplexity.ai/categories.md) · [Tags](https://community.perplexity.ai/tags.md) **Page:** 16 --- ## [What is the max input token for api request?](https://community.perplexity.ai/t/what-is-the-max-input-token-for-api-request/82)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:14am UTC](https://community.perplexity.ai/t/what-is-the-max-input-token-for-api-request/82 "2025-05-15T00:14:20Z")
What is the max input token for api request? --- ## [Mixed Results with Perplexity API](https://community.perplexity.ai/t/mixed-results-with-perplexity-api/81)
**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")
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… --- ## [Web search not being performed](https://community.perplexity.ai/t/web-search-not-being-performed/80)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:14am UTC](https://community.perplexity.ai/t/web-search-not-being-performed/80 "2025-05-15T00:14:09Z")
I’m submitting a “system” prompt with some examples, and then a “user” prompt similar to below, asking it to search the internet. Up until a week or 2 ago, this was consistently working and searching the internet correct… --- ## [Technical Help: Which Tokenizer for Perplexity LLaMa Models?](https://community.perplexity.ai/t/technical-help-which-tokenizer-for-perplexity-llama-models/79)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:14am UTC](https://community.perplexity.ai/t/technical-help-which-tokenizer-for-perplexity-llama-models/79 "2025-05-15T00:14:03Z")
Hi everyone! Does anyone know which tokenizer (and library) we should use to count tokens the exact way the Perplexity models do it? I’m integrating Perplexity’s LLaMa 3.1 models (small/large/huge online and small/larg… --- ## [Beta features access](https://community.perplexity.ai/t/beta-features-access/78)
**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")
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… --- ## [Search\_domain\_filter not working, getting citations outside my domain list](https://community.perplexity.ai/t/search-domain-filter-not-working-getting-citations-outside-my-domain-list/77)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 4\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/search-domain-filter-not-working-getting-citations-outside-my-domain-list/77 "2025-05-15T00:13:54Z")
Hi all, I’m trying to make a api request like this url = "https://api.perplexity.ai/chat/completions" payload = { "model": "llama-3.1-sonar-large-128k-online", "messages": \[ { … --- ## [Llama-3.1-sonar-small-128k-online not using web look-up](https://community.perplexity.ai/t/llama-3-1-sonar-small-128k-online-not-using-web-look-up/76)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/llama-3-1-sonar-small-128k-online-not-using-web-look-up/76 "2025-05-15T00:13:41Z")
I cannot get llama-3.1-sonar-small-128k-online to perform web look-ups, and it always produces results stating it is “unable to search the internet in real-time or access specific company databases directly”, is it possi… --- ## [Is there an option to upload a document and then ask questions about it in Perplexity API?](https://community.perplexity.ai/t/is-there-an-option-to-upload-a-document-and-then-ask-questions-about-it-in-perplexity-api/75)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/is-there-an-option-to-upload-a-document-and-then-ask-questions-about-it-in-perplexity-api/75 "2025-05-15T00:13:34Z")
Hey, I wanted to know if its possible to upload documents and then asking questions related to it via Perplexity API? I couldn’t find anything related to it in the documentation. --- ## [API: Unable to use the "llama-3.1-sonar-huge-128k-online" model](https://community.perplexity.ai/t/api-unable-to-use-the-llama-3-1-sonar-huge-128k-online-model/74)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/api-unable-to-use-the-llama-3-1-sonar-huge-128k-online-model/74 "2025-05-15T00:13:28Z")
Summary I’m having trouble calling the “llama-3.1-sonar-huge-128k-online” model. When I make the call, I see that the request is being made. It takes about 60 seconds, then returns an error. Note: Using the “llama-3.1-… --- ## [Perplexity unable or unwilling to link amazon products?](https://community.perplexity.ai/t/perplexity-unable-or-unwilling-to-link-amazon-products/72)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/perplexity-unable-or-unwilling-to-link-amazon-products/72 "2025-05-15T00:13:13Z")
I am trying to make an assistant that finds highly rated books on Amazon that cover a requested topic. I am using Perplexity API as well as trying on the perplexity.ai. I am finding that the results are fantastic, but fo… --- ## [Is every API call separate?](https://community.perplexity.ai/t/is-every-api-call-separate/70)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:13am UTC](https://community.perplexity.ai/t/is-every-api-call-separate/70 "2025-05-15T00:13:02Z")
I don’t see anything suggesting that a sequence of API calls are linked together as a conversation. So I guess the question is: Is each API call an isolated request? Is there a way I can have the same backend app mana… --- ## [Pro Search API](https://community.perplexity.ai/t/pro-search-api/68)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/pro-search-api/68 "2025-05-15T00:12:49Z")
Is there a plan or maybe even a timeline for pro search via API? --- ## [Sources for perplexity](https://community.perplexity.ai/t/sources-for-perplexity/67)
**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")
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)
**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")
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)
**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")
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? --- ## [Will we be getting Sonar Huge chat or llama-3.1-405B-instruct as options?](https://community.perplexity.ai/t/will-we-be-getting-sonar-huge-chat-or-llama-3-1-405b-instruct-as-options/64)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 0\ **Last updated:** [May 15, 2025, 12:12am UTC](https://community.perplexity.ai/t/will-we-be-getting-sonar-huge-chat-or-llama-3-1-405b-instruct-as-options/64 "2025-05-15T00:12:15Z")
Will we be getting llama-3.1-sonar-huge-128k-chat or llama-3.1-405B-instruct as options? also, will we ever see llama-3.2? --- ## [Many HTTP status code 524 errors for API responses](https://community.perplexity.ai/t/many-http-status-code-524-errors-for-api-responses/63)
**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")
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)
**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")
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… --- ## [Perplexity API doesn't support tool call, even though Llama 3.1 does](https://community.perplexity.ai/t/perplexity-api-doesnt-support-tool-call-even-though-llama-3-1-does/61)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/perplexity-api-doesnt-support-tool-call-even-though-llama-3-1-does/61 "2025-05-15T00:11:59Z")
Perplexity API doesn’t support tool call, even though Llama 3.1 does. So will it be supported in the future? --- ## [API token usage reports and billing](https://community.perplexity.ai/t/api-token-usage-reports-and-billing/60)
**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")
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? --- ## [Cannot use spring-ai-openai-spring-boot-starter](https://community.perplexity.ai/t/cannot-use-spring-ai-openai-spring-boot-starter/59)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/cannot-use-spring-ai-openai-spring-boot-starter/59 "2025-05-15T00:11:46Z")
I wish to use spring-ai-openai-spring-boot-starter to develop my application. The library (as many other libraries do) adds /v1 to the configured spring.ai.openai.base-url=https://api.perplexity.ai/ resulting in a call … --- ## [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)
**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")
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 … --- ## [About Perplexity Data](https://community.perplexity.ai/t/about-perplexity-data/57)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/about-perplexity-data/57 "2025-05-15T00:11:31Z")
I am using Perplexity to fetch events by location name and date. But I got inaccurate data. Can you please let me know when i hit same prompt hit on preplexity UI I got accurate data and another side when i pass same pr… --- ## [Bare minimum example on website is wrong](https://community.perplexity.ai/t/bare-minimum-example-on-website-is-wrong/56)
**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")
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)
**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")
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… --- ## [Api request speed is very slow, is there any solution？](https://community.perplexity.ai/t/api-request-speed-is-very-slow-is-there-any-solution/54)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 2\ **Last updated:** [May 15, 2025, 12:11am UTC](https://community.perplexity.ai/t/api-request-speed-is-very-slow-is-there-any-solution/54 "2025-05-15T00:11:07Z")
I found that the website was also slow the first time, but after each time answered questions quickly ， But I need to call this API, https://api.perplexity.ai/chat/completions, each time is slow, how to solve? --- ## [Stream responses are 5s slow to get the first token](https://community.perplexity.ai/t/stream-responses-are-5s-slow-to-get-the-first-token/53)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/stream-responses-are-5s-slow-to-get-the-first-token/53 "2025-05-15T00:10:58Z")
Hello, for my usecase I need very low latencies with llama-3.1-sonar-huge-128k-online but currently the model is very slow to respond in streaming requests. The 70b would already be enough with speedness but is it not co… --- ## [Why is the model not using online search?](https://community.perplexity.ai/t/why-is-the-model-not-using-online-search/52)
**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")
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)
**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")
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? --- ## [API not returning multiple responses with top\_k \> 1 and top\_p ≈ 1](https://community.perplexity.ai/t/api-not-returning-multiple-responses-with-top-k-1-and-top-p-1/50)
**Author:** [@vikvang](https://community.perplexity.ai/u/vikvang)\ **Replies:** 1\ **Last updated:** [May 15, 2025, 12:10am UTC](https://community.perplexity.ai/t/api-not-returning-multiple-responses-with-top-k-1-and-top-p-1/50 "2025-05-15T00:10:36Z")
Issue Description The Perplexity AI API is not returning multiple responses when the top\_k parameter is set to a value greater than 1 and the top\_p parameter is close to 1. This behavior is inconsistent with the expecte… [Previous page](https://community.perplexity.ai/latest.md?page=14) [Next page](https://community.perplexity.ai/latest.md?page=16)