# AI exceeds LLM token thresholds randomly and unpredictably

**URL:** https://meta.discourse.org/t/ai-exceeds-llm-token-thresholds-randomly-and-unpredictably/402334
**Category:** Support
**Tags:** ai
**Created:** [May 6, 2026, 6:02pm UTC](https://meta.discourse.org/t/ai-exceeds-llm-token-thresholds-randomly-and-unpredictably/402334 "2026-05-06T18:02:20Z")
**Posts on this page:** 1
**Showing post:** 4

<div class="post-metadata">

### Author: ![RBoy](https://avatars.discourse-cdn.com/v4/letter/r/2bfe46/32.png) [@RBoy](https://meta.discourse.org/u/RBoy)
#### Post date: [May 6, 2026, 7:01pm UTC](https://meta.discourse.org/t/ai-exceeds-llm-token-thresholds-randomly-and-unpredictably/402334/4 "2026-05-06T19:01:15Z")

</div>

Just FYI the problem first started with the translation service getting stuck and running out of tokens:

> DiscourseAi::Completions::Endpoints::OpenAi: status: 429 - body: {“error”:{“message”:“Rate limit reached for model `openai/gpt-oss-120b` in organization `org_01kccx1be8fffaz5sbe17` service tier `on_demand` on tokens per day (TPD): Limit 200000, Used 193487, Requested 7464. Please try again in 6m50.832s. Need more tokens? Upgrade to Dev Tier today at [https://console.groq.com/settings/billing",“type”:“tokens”,“code”:"rate\_limit\_exceeded](https://console.groq.com/settings/billing%22,%22type%22:%22tokens%22,%22code%22:%22rate_limit_exceeded)”}}

Then I paused the service for 24 hours for the daily rate limits to reset. After restarting it then I noticed this error:

> DiscourseAi::Completions::Endpoints::OpenAi: status: 413 - body: {“error”:{“message”:“Request too large for model `openai/gpt-oss-120b` in organization `org_01kccx1be8fffaz5sbe17` service tier `on_demand` on tokens per minute (TPM): Limit 8000, Requested 8102, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at [https://console.groq.com/settings/billing",“type”:“tokens”,“code”:"rate\_limit\_exceeded](https://console.groq.com/settings/billing%22,%22type%22:%22tokens%22,%22code%22:%22rate_limit_exceeded)”}}

Then I reduced max output tokens from 7000 to 6800 in the LLM configuration and it started working again.

What am I missing here? Are you suggesting it’s related to context window and nothing to do with max output tokens? Just trying to figure out how to match configuration numbers from groq / model limits to discourse LLM configurations.

---

_[View the full topic](https://meta.discourse.org/t/ai-exceeds-llm-token-thresholds-randomly-and-unpredictably/402334)._