@BerriAI
The fastest way to take your LLM app to production
Analyzed 5h ago
Repos Analyzed
30
With LLM Usage
4
Total Call Sites
10
LLM Providers
2
LLM Providers
Models
Frameworks
Estimate costs using published model pricing and your own volume inputs.
Model
Daily API Calls
1,000Avg Tokens per Request
1,000gpt-4o pricing
Input: $2.5/1M tokens · Output: $10/1M tokens
These estimates use published model pricing. Actual costs depend on your call volume, prompt length, and response size.
