web
You’re offline. This is a read only version of the page.
close
Skip to main content

Announcements

News and Announcements icon
Community site session details

Community site session details

Session Id :
Power Platform Community / Forums / Copilot Studio / Agent only answers wit...
Copilot Studio
Suggested Answer

Agent only answers with error message in MS Teams

(1) ShareShare
ReportReport
Posted on by 10
Our agent only answers this when asked any question in MS Teams:
 
Ein Fehler ist aufgetreten. Fehlercode: OpenAIModelTokenLimit Unterhaltungs-ID: a:10HMwIRZDblnnzYKSeWIHUrx5RddpmuaOhX1U8S386qmDnODyEvvDeI89f90DyD4pgLi8O-DFpguq7A9j87YO8R2A-byLJm3u4LnUZCs-bR1lBusNfAVOynAOvRHOXwAA Zeit (UTC): 2026-05-11T08:15:31.377Z.
 
I already tried "start over", "Neustart", starting a new chat in MS Teams, restarting teams but that didn't solve the problem.
 
How can we continue using that agent in MS Teams?
How can we assure that this doesn't happen in future to any of our employees?
 
Best,
Reiner
 
I have the same question (0)
  • Suggested answer
    sumit_artesian Profile Picture
    261 on at
     
    Are you by any chance using an AI model? Like maybe using a GPT or a Gemini model or an AI Builder to perform a certain task? Based on your error response, it appears the error is due to the OpenAI Model Token Limit. This means you have exhausted your valid tokens for the model.
     
    When using an AI model, we basically communicate with the LLM using API requests. Each API request contains an input JSON, which is the system instructions and your prompt, and an output JSON, which is the model's response to your prompt. And both input and output JSONs consume tokens based on the number of characters used. So larger input instructions and prompts will consume more input tokens, and larger responses consume more output tokens.
     
    Based on your error code, it seems you have reached your model's limit. You can either wait for your limit to reset or you can upgrade your model to allow for greater tokens.
     
    Quick tip: Try to keep your input instructions small and use a prompt that tells the model to minimize the output response, if possible, to optimize the token consumption.
     

    Please  Does this answer your question if my post helped you solve your issue. This will help others find it more readily. It also closes the item.
    If the content was useful in other ways, please consider answering Yes to Was this reply helpful? or give it a Like! 🩷

Under review

Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.

Helpful resources

Quick Links

Season of Sharing Community Challenge Launch!

Jump in, show your community spirit, and win prizes!

Kudos to our 2025 Community Spotlight Honorees

Expanding mentorship, skilling, and AI innovation

Congratulations to the May Top 10 Community Leaders!

These are the community rock stars!

Leaderboard > Copilot Studio

#1
Valantis Profile Picture

Valantis 277

#2
11manish Profile Picture

11manish 206

#3
sannavajjala87 Profile Picture

sannavajjala87 156 Super User 2026 Season 1

Last 30 days Overall leaderboard