API Usage Logs
Monitor your xBesh LLM API calls, tokens, and costs
Total Calls
1,247
This month
Success Rate
96.8%
+2.4% from last month
Total Tokens
125,340
Input + Output
Total Cost
$2.51
This month
Avg Latency
0.9s
-0.2s improvement
Recent API Calls
Real-time log of your xBesh LLM API requests
/v1/chat/completions
200
January 15, 2024•ID: log_001
$0.0248
1.2s
Model:
xbesh-gpt-4
Tokens: 1,240
/v1/embeddings
200
January 15, 2024•ID: log_002
$0.0005
0.4s
Model:
xbesh-ada-002
Tokens: 512
/v1/chat/completions
200
January 15, 2024•ID: log_003
$0.0017
0.8s
Model:
xbesh-gpt-3.5
Tokens: 856
/v1/chat/completions
429
January 15, 2024•ID: log_004
$0.00
0.1s
Model:
xbesh-gpt-4
Tokens: 0
Rate limit exceeded
/v1/completions
200
January 15, 2024•ID: log_005
$0.0410
2.1s
Model:
xbesh-davinci
Tokens: 2,048
/v1/chat/completions
200
January 15, 2024•ID: log_006
$0.0013
0.6s
Model:
xbesh-gpt-3.5
Tokens: 645
/v1/embeddings
200
January 15, 2024•ID: log_007
$0.0010
0.5s
Model:
xbesh-ada-002
Tokens: 1,024
/v1/chat/completions
401
January 15, 2024•ID: log_008
$0.00
0.2s
Model:
xbesh-gpt-4
Tokens: 0
Invalid API key
Usage Tips
1
Monitor your usage
Keep track of API calls to stay within your plan limits (10,000/month for Pro)
2
Optimize token usage
Reduce costs by using shorter prompts and appropriate models for your tasks
3
Handle errors gracefully
Implement retry logic for rate limits and proper error handling in your applications