Limits & Quotas Overview

Requests: 60 per hour (1 per minute)
Burst: 10 requests in 1 minute
Reset: Rolling 60-minute window
```text

**Pro Plan:**
```text
Requests: 1,000 per hour (~17 per minute)
Burst: 100 requests in 1 minute
Reset: Rolling 60-minute window
```text

**Team Plan:**
```text
Requests: 10,000 per hour (~167 per minute)
Burst: 500 requests in 1 minute
Reset: Rolling 60-minute window
```text

### Interactive Rate Limits

**Chat Messages:**
- Free: 20 messages per hour
- Pro: 500 messages per hour
- Team: 2,000 messages per hour

**File Uploads:**
- Free: 5 files per month
- Pro: 100 files per day
- Team: 1,000 files per day

**Agent Executions:**
- Free: 5 per day
- Pro: 100 per day
- Team: 1,000 per day

## Storage and Memory Limits

### File Storage

**Storage Allocation by Plan:**
```text
Free: 100MB total
├── Documents: Up to 50MB
├── Images: Up to 30MB
└── Other files: Up to 20MB

Pro: 10GB total
├── Documents: Up to 5GB
├── Images: Up to 3GB
└── Other files: Up to 2GB

Team: 100GB total
├── Shared storage: 80GB
└── Individual storage: 20GB per member
```text

### File Size Limits

**Individual File Limits:**
- **Documents**: 25MB per file
- **Images**: 10MB per file
- **Code files**: 5MB per file
- **Spreadsheets**: 15MB per file

**Processing Limits:**
- **OCR documents**: 100 pages per file
- **Image analysis**: 4K resolution maximum
- **Code analysis**: 50,000 lines per file

### Memory System Limits

**Memory Entries:**
```text
Free Plan:
├── Total entries: 50
├── Entry size: 500 characters
└── Search results: 5 per query

Pro Plan:
├── Total entries: 1,000
├── Entry size: 2,000 characters
└── Search results: 20 per query

Team Plan:
├── Total entries: 10,000
├── Entry size: 5,000 characters
└── Search results: 50 per query
```text

## Model-Specific Limits

### Context Window Limits

**By Model:**
```text
GPT-4o: 128,000 tokens
├── Effective context: ~120,000 tokens
├── System prompts: ~2,000 tokens
└── Response buffer: ~6,000 tokens

Claude 4 Sonnet: 1,000,000 tokens
├── Effective context: ~990,000 tokens
├── System prompts: ~3,000 tokens
└── Response buffer: ~7,000 tokens

Claude 3.5 Sonnet: 200,000 tokens
├── Effective context: ~190,000 tokens
├── System prompts: ~3,000 tokens
└── Response buffer: ~7,000 tokens

o1-preview: 128,000 tokens
├── Effective context: ~100,000 tokens
├── Reasoning space: ~20,000 tokens
└── Response buffer: ~8,000 tokens
```text

### Processing Timeouts

**Request Timeouts:**
- **Simple queries**: 30 seconds
- **Complex analysis**: 5 minutes
- **Agent execution**: 15 minutes
- **File processing**: 10 minutes

**Background Processing:**
- **Large file analysis**: 30 minutes
- **Batch operations**: 1 hour
- **Report generation**: 2 hours

### Concurrent Request Limits

**Simultaneous Requests:**
```text
Free: 1 concurrent request
Pro: 5 concurrent requests
Team: 20 concurrent requests
Enterprise: 100+ concurrent requests
```text

## Performance Limits

### Response Time Targets

**Service Level Objectives (SLOs):**
```text
Chat responses: 95% under 3 seconds
File uploads: 95% under 10 seconds
Search queries: 95% under 2 seconds
Agent execution: 90% under 30 seconds
```text

### Throughput Limits

**Platform Capacity:**
- **Peak concurrent users**: 100,000+
- **Messages per second**: 10,000+
- **File uploads per hour**: 50,000+
- **API requests per second**: 5,000+

## Monitoring and Alerts

### Usage Dashboards

Track your current usage against limits:

```text
📊 Current Usage Status:
├── API Requests: 450/1,000 per hour (45%)
├── Storage: 2.3GB/10GB (23%)
├── Monthly Tokens: 45,230/100,000 (45%)
└── Concurrent Chats: 3/10 (30%)
```text

### Automatic Alerts

**Limit Approach Warnings:**
```text
🟡 Warning: 75% of limit reached
🟠 Caution: 90% of limit reached
🔴 Critical: 95% of limit reached
⛔ Blocked: 100% of limit reached
```text

### Custom Thresholds

Set personalized alert levels:
- **Budget alerts**: Custom percentage thresholds
- **Storage alerts**: Custom GB thresholds
- **Usage alerts**: Custom daily/weekly limits

## Limit Increases

### Automatic Scaling

**Plan Upgrades:**
- Instant limit increases upon plan upgrade
- Prorated billing for mid-cycle upgrades
- Immediate access to higher tier limits

### Custom Limits (Enterprise)

**Available Customizations:**
- **Rate limits**: Custom API request rates
- **Storage**: Dedicated storage allocations
- **Concurrency**: Higher parallel processing
- **Timeouts**: Extended processing windows

### Temporary Increases

**Special Circumstances:**
- **Event-based scaling**: Higher limits during launches
- **Seasonal adjustments**: Increased capacity for peak periods
- **Migration assistance**: Temporary higher limits during onboarding

## Best Practices

### Staying Within Limits

**Rate Limit Management:**
- Implement exponential backoff in API clients
- Use batch processing for bulk operations
- Cache responses to reduce redundant requests

**Storage Optimization:**
- Regularly clean up unused files
- Compress large documents before upload
- Use external storage for large datasets

**Token Efficiency:**
- Optimize prompts for clarity and brevity
- Use appropriate models for task complexity
- Implement context management strategies

### Planning for Growth

**Usage Forecasting:**
- Monitor growth trends in usage dashboards
- Plan plan upgrades before hitting limits
- Consider enterprise options for predictable scaling

**Architecture Design:**
- Design systems to handle rate limiting gracefully
- Implement proper error handling for limit exceptions
- Use asynchronous processing for large operations

## Troubleshooting Limits

### Common Limit Issues

**1. Rate Limit Exceeded**
```text
Error: "Rate limit exceeded. Try again in 42 seconds."
Solution: Implement retry logic with exponential backoff
```text

**2. Storage Quota Full**
```text
Error: "Storage quota exceeded. Free up space to continue."
Solution: Delete unused files or upgrade plan
```text

**3. Context Window Exceeded**
```text
Error: "Input too long for model context window."
Solution: Reduce conversation history or file size
```text

### Resolution Strategies

**Immediate Actions:**
- Wait for rate limit reset periods
- Delete unnecessary files to free storage
- Switch to models with larger context windows

**Long-term Solutions:**
- Upgrade to higher plan tier
- Implement usage optimization strategies
- Consider enterprise custom limits

## Next Steps

- [Learn about rate limits in detail](/limits/rate-limits)
- [Understand storage limitations](/limits/storage)
- [Explore model-specific limits](/limits/models)

## Related Resources

- [Token Usage](/tokens/overview)
- [Billing & Pricing](/tokens/billing)
- [Account Management](/account/overview)