Ftn - Host Custom LLM Models

Fine tuned LLama/GPT-2 but hosting is expensive and time consuming?

Just upload your pth or tf files and we'll automatically host your model.

Inference

FTN exposes an API for inference

curl -X POST \
 -H "Content-Type: application/json" \
 -d '{"prompt": "Imagine something", "maxTokens": 200}' \
 https://api.nevin.cc/generate

Pricing