# Standard embeddings — x-ratelimit-limit meters input texts, not requests; documented 512-text batch unreachable at Tier 1 **URL:** \ **Category:** Bug Reports\ **Tags:** api, embeddings-api\ **Created:** [August 26, 2026, 6:08am UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914 "2026-08-26T06:08:18Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![dbrickner](https://avatars.discourse-cdn.com/v4/letter/d/e19b73/32.png) [@dbrickner](https://community.perplexity.ai/u/dbrickner)\ **Post date:** [August 26, 2026, 6:08am UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/1 "2026-08-26T06:08:19Z")
## Pre-flight checklist - This is about the Perplexity API, not the Perplexity app, Comet, or web UI. - I have removed API keys, secrets, and private data. - I have included enough information for someone else to reproduce the issue. ## Bug type - Error response or failed request - Incorrect or unexpected model output - Missing, invalid, or stale citations/search results - Streaming issue - Structured output or JSON schema issue - SDK issue - Billing, credits, or rate limit issue - Dashboard, API key, or auth issue - Other API bug ## Affected API area - Agent API - Search API - Sonar API - Embeddings API - SDKs - Dashboard, API keys, or auth - Billing or credits - Not sure ## Summary The Tier 1 QPS limit is being treated as a texts limit. Unable to send up to 512 texts per request, any texts past 167 in a second fail. ## Expected behavior Able to send up to 167/QPS with each query/call having up to 512 texts to be embedded. These are short texts of 270 tokens or less. ## Actual behavior Response body on failure: {“error”:{“message”:“Rate limit exceeded, please try again later.”,“type”:“request\_rate\_limit\_exceeded”,“code”:429}} The core observation. x-ratelimit-limit is 167, and a single request consumes one unit per input text rather than one unit per request: - 1 request of 3 texts → x-ratelimit-used: 3 - 1 request of 100 texts → x-ratelimit-used: 100 - 1 request of 167 texts → x-ratelimit-used: 167, remaining: 0 Twenty simultaneous 50-text requests produced exactly three successes, with x-ratelimit-used reading 50, 100 and 150; the fourth would have reached 200 and was refused. Ten simultaneous 100-text requests produced one success. Under a requests-per-second model these should have been 20/20 and 10/10. Consequently any request whose text count exceeds 167 is refused regardless of client idle time (tested to 40 s), which makes the documented maximum unreachable on this account: ┌─────────┬────────┐ │ n texts │ Result │ ├─────────┼────────┤ │ 167 │ 200 │ ├─────────┼────────┤ │ 168 │ 429 │ ├─────────┼────────┤ │ 200 │ 429 │ ├─────────┼────────┤ │ 256 │ 429 │ ├─────────┼────────┤ │ 400 │ 429 │ ├─────────┼────────┤ │ 512 │ 429 │ └─────────┴────────┘ ## Minimal reproduction ```python Confirmed — reproduces on the first call after 45 s idle. Twelve lines, no dependencies beyond requests: ``` ```python import os, requests r = requests.post( "https://api.perplexity.ai/v1/embeddings", headers={"Authorization": f"Bearer {os.environ['PERPLEXITY_API_KEY']}"}, json={"model": "pplx-embed-v1-4b", "input": [f"text number {i}" for i in range(200)]}, ) print(r.status_code) print(r.text) ``` ```python Control: change range(200) to range(167) and the identical script returns 200 with 167 embeddings. That single-character difference is the whole bug. ``` ## Response or error ```json HTTP/1.1 429 CF-RAY: a310919b3fb133a6-EWR Connection: keep-alive Content-Length: 116 Content-Type: application/json Date: Wed, 26 Aug 2026 05:52:09 GMT Server: cloudflare Strict-Transport-Security: max-age=15552000; includeSubDomains; preload access-control-allow-origin: * cf-cache-status: DYNAMIC set-cookie: __cf_bm=;__ cflb= x-request-id: 1fac928d-2a12-48f0-827a-731348ee4772 {"error":{"message":"Rate limit exceeded, please try again later.","type":"request_rate_limit_exceeded","code":429}} That's the complete header set — no x-ratelimit-limit, -remaining, -used or -reset at all, which is the detail worth their attention. ``` ## Request details - Endpoint: POST [https://api.perplexity.ai/v1/embeddings](https://api.perplexity.ai/v1/embeddings) - Model or preset: pplx-embed-v1-4b - SDK/language/version: Python 3.12, requests 2.34.2 (also reproduced with httpx 0.28 sync and async — not SDK-specific) - Request ID: 62bdcf5c-f86a-4a3c-a28e-6943b1ac582a - Approximate time and timezone: (UTC): 05:48:48 - Consistent or intermittent: Consistent ## Additional context ---
**Author:** ![andrewmadson-pplx](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/andrewmadson-pplx/32/3428_2.png) [@andrewmadson-pplx](https://community.perplexity.ai/u/andrewmadson-pplx)\ **Post date:** [September 4, 2026, 8:03pm UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/2 "2026-09-04T20:03:50Z")
Hello @dbrickner , Thank you for reporting this. I have followed up with the team and will let you know what I find. Andrew ---
**Author:** ![dbrickner](https://avatars.discourse-cdn.com/v4/letter/d/e19b73/32.png) [@dbrickner](https://community.perplexity.ai/u/dbrickner)\ **Post date:** [September 19, 2026, 11:12pm UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/3 "2026-09-19T23:12:18Z")
Hello Andrew, Thanks for taking a look at this. Has there been any progress? The performance we have now is orders of magnitude less than when we first tested the embeddings months ago and the slow speed is going to be bottleneck in a few days when we start embedding our corpus. ---
**Author:** ![andrewmadson-pplx](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/andrewmadson-pplx/32/3428_2.png) [@andrewmadson-pplx](https://community.perplexity.ai/u/andrewmadson-pplx)\ **Post date:** [September 21, 2026, 9:48pm UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/4 "2026-09-21T21:48:38Z")
Hello @dbrickner , Yes - the team is working on an update. I am monitoring for it to go live. Thank you for your patience. ---
**Author:** ![andrewmadson-pplx](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/andrewmadson-pplx/32/3428_2.png) [@andrewmadson-pplx](https://community.perplexity.ai/u/andrewmadson-pplx)\ **Post date:** [September 22, 2026, 10:04pm UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/5 "2026-09-22T22:04:11Z")
Hi @dbrickner, thanks for your patience. The update is now live in production. Standard embeddings batches now count as one request against the rate limit instead of one unit per input text, so batches over 167 texts should no longer return 429 at Tier 1. ---
**Author:** ![dbrickner](https://avatars.discourse-cdn.com/v4/letter/d/e19b73/32.png) [@dbrickner](https://community.perplexity.ai/u/dbrickner)\ **Post date:** [September 23, 2026, 8:14pm UTC](https://community.perplexity.ai/t/standard-embeddings-x-ratelimit-limit-meters-input-texts-not-requests-documented-512-text-batch-unreachable-at-tier-1/5914/6 "2026-09-23T20:14:05Z")
Confirming that this is now working and throughput on the standard endpoint is now about 4.5x higher. There is a new limit being hit which is 4096 embeddings in flight at a time. If there is latency in completing the embeddings this can be hit and start producing 429s. Depending upon latency, we are not getting between 715/s and 830/s. Much improved. I also began testing the context endpoint and it has the same problem as the standard endpoint that you have just resolved. I’ll submit that as a separate Bug Report here.