Base URL

Our API is hosted at https://api.gpt-research.org

Note: if you want to use a custom model from a hosted GPT-Research Hub, your custom API endpoint will be shown on the model's page.

POST /api/v1/inference

Endpoint to perform text generation using a prompt and model.

Example Request (cURL):

curl -X POST \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Your prompt text here", "model":"ModelName"}' \
  https://api.gpt-research.org/api/v1/inference
            

Example Request (JavaScript - fetch):

fetch('https://api.gpt-research.org/api/v1/inference', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({ prompt: 'Your prompt text here', model: 'ModelName' })
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
            

Example Response:

{
  "result": "Generated text here"
}
            

GET /api/v1/inference

Endpoint to perform text generation using a prompt and model via query parameters.

Example Request (cURL):

curl -X GET \
  "https://api.gpt-research.org/api/v1/inference?prompt=Your+prompt+text+here&model=ModelName"
            

Example Request (JavaScript - fetch):

fetch('https://api.gpt-research.org/api/v1/inference?prompt=Your+prompt+text+here&model=ModelName')
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
            

Example Response:

{
  "result": "Generated text here"
}