§ Library · Centralized Model Registry
Model Registry
Discover and compare all deployed and fine-tuned models. Browse training metrics, benchmarks, and usage statistics.
Total Models
3
Fine-Tuned
2
In Production
3
Total Requests (30d)
662k
3 models found
GPT-4 (Base Model)
ID: gpt-4o
production
OpenAI GPT-4 base model. Highly capable for general-purpose tasks, reasoning, and content creation.
Latency
450ms
Throughput
45 t/s
Accuracy
Base
450k reqs
95/100
Llama 3.2 3B (Customer Support Fine-Tuned)
ID: llama-3.2-3b-ft-001
Fine-tuned
production
Fine-tuned Llama 3.2 3B optimized for customer support conversations with high accuracy on FAQs.
Latency
245ms
Throughput
78 t/s
Accuracy
94.2%
125k reqs
92/100
Mistral 7B (Product Q&A)
ID: mistral-7b-ft-001
Fine-tuned
production
Mistral 7B fine-tuned for product-specific Q&A with excellent accuracy on domain questions.
Latency
312ms
Throughput
65 t/s
Accuracy
91.8%
87k reqs
78/100
📚 About this registry: All deployed and fine-tuned models are automatically indexed here. Each model includes training metrics, performance benchmarks, dataset sources, and usage statistics. Filter by type, provider, or tags to find the right model for your use case.