How does Github Models Rate-Limiting work #137298
-
| Select Topic AreaQuestion BodyGPT 4o mini has a rate limit of 150/day | 
Beta Was this translation helpful? Give feedback.
Replies: 6 comments 9 replies
-
| Yes, you can use a total of 200 requests per day if you combine the rate limits of GPT-4o mini (150/day) and GPT-4o (50/day). However, if each of the 25 models has its own rate limit, then theoretically, you could make up to 2000 requests per day (25 models * 80 requests/day). But this depends on the specific rate limits set for each model and whether they can be combined in this way. | 
Beta Was this translation helpful? Give feedback.
        
          
            
              This comment was marked as off-topic.
            
          
            
        
      
    
            
              This comment was marked as off-topic.
            
          
            
        
        
          
            
              This comment was marked as off-topic.
            
          
            
        
      
    
            
              This comment was marked as off-topic.
            
          
            
        -
| Why? This is a system that users pay to use. There's a transaction here. If you buy or rent a product, it’s absurd for it to stop in the middle of doing its job and say, “I’m not working, wait.” There’s no other subscription system in the world like that. Right now, AI is expensive, so everyone is doing the same thing, and saying “we’re doing it too” is, in my opinion, completely wrong. I believe many people feel the same way. If it were free, I’d understand the fair use part, but for a service we’re paying for to refuse to work doesn’t align with how things work in the real world. Even if you put a clause in the user agreement saying “this is how it works, take it or leave it,” it still doesn’t justify the situation. | 
Beta Was this translation helpful? Give feedback.
-
| dddddd | 
Beta Was this translation helpful? Give feedback.
-
| #!/data/data/com.termux/files/usr/bin/bash Filename and repo infoLOGFILE="$HOME/gov-appstore-setup-20250823-122134.log" 1. Check for log fileif [ ! -f "$LOGFILE" ]; then 2. Show log contentsecho "----- LOG CONTENTS -----" 3. Redact sensitive infoREDACTED_LOG="$HOME/gov-appstore-setup-20250823-122134.redacted.log" echo "----- REDACTED LOG -----" 4. Push to GitHubecho "Enter your GitHub Personal Access Token:" cd ~ echo "Log pushed to GitHub repository: https://github.com/${GITHUB_USER}/${GITHUB_REPO}/tree/${GITHUB_BRANCH}" | 
Beta Was this translation helpful? Give feedback.
Yes, you can use a total of 200 requests per day if you combine the rate limits of GPT-4o mini (150/day) and GPT-4o (50/day).
However, if each of the 25 models has its own rate limit, then theoretically, you could make up to 2000 requests per day (25 models * 80 requests/day). But this depends on the specific rate limits set for each model and whether they can be combined in this way.