Skip to content

GPT-2: Text Generation

This models provides text generation based an initial input text. It's based on the largest GPT-2 algorithm available with 1.5 billion parameters and it provides state of the art results in text generation. It's API exposes multiple parameters that control the generated text to get better performance in different scenarios.


  • The largest available GPT-2 model with 1.5 billion parameters
  • State of the art results in text generation
  • Multiple parameters to control the generated text allows for great performance in different scenarios.
  • Only pay for what you use with a simple metered pricing model
  • Same price independent of the resources (memory/cpu/gpu) used

Learn how to launch this algorithm in AWS SageMaker and see examples from the actual API.


This model has a fee of 0.15 dollars per hour. You will incur costs for software use only for as long the endpoint is running.

AWS infrastructure costs are independent and in addition to the costs of the software and it depends on the instance type selected to host the algorithm.