Standard or fine-tuned models

Deploy standard GPT-J or train a fine-tuned model for absolutely free

Lightning-fast inference

Inference speeds comparable to a TPU v2 and v3 at various token lengths

Usage logs

Built-in usage logs displaying inputs and outputs for all of your GPT-J deployments

Flat-rate pricing

Flat-rate pricing with unlimited usage at a 33% discount compared to a TPU v2

See GPT-J in action

Your submission has been received! We'll be in touch with you shortly.
Oops! Something went wrong while submitting the form.