Edits

Given a prompt and an instruction, the model will return an edited version of the prompt.

Create edit

POST https://api.openai.com/v1/edits

Creates a new edit for the provided input, instruction, and parameters.

Request body

---

modelstringRequired

ID of the model to use. You can use the text-davinci-edit-001 or code-davinci-edit-001 model with this endpoint.

---

inputstringOptionalDefaults to ''

The input text to use as a starting point for the edit.

---

instructionstringRequired

The instruction that tells the model how to edit the prompt.

---

nintegerOptionalDefaults to 1

How many edits to generate for the input and instruction.

---

temperaturenumberOptionalDefaults to 1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

We generally recommend altering this or top_p but not both.

---

top_pnumberOptionalDefaults to 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

---

text-davinci-edit-001

Example request:

curl:

curl https://api.openai.com/v1/edits \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "text-davinci-edit-001",
    "input": "What day of the wek is it?",
    "instruction": "Fix the spelling mistakes"
  }'

python:

import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.Edit.create(
  model="text-davinci-edit-001",
  input="What day of the wek is it?",
  instruction="Fix the spelling mistakes"
)

node.js:

const { Configuration, OpenAIApi } = require("openai");
const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);
const response = await openai.createEdit({
  model: "text-davinci-edit-001",
  input: "What day of the wek is it?",
  instruction: "Fix the spelling mistakes",
});

Parameters:

{
  "model": "text-davinci-edit-001",
  "input": "What day of the wek is it?",
  "instruction": "Fix the spelling mistakes",
}

Response:

{
  "object": "edit",
  "created": 1589478378,
  "choices": [
    {
      "text": "What day of the week is it?",
      "index": 0,
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 32,
    "total_tokens": 57
  }
}

code-davinci-edit-001

Example request:

curl:

curl https://api.openai.com/v1/edits \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "code-davinci-edit-001",
    "input": "What day of the wek is it?",
    "instruction": "Fix the spelling mistakes"
  }'

python:

import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.Edit.create(
  model="code-davinci-edit-001",
  input="What day of the wek is it?",
  instruction="Fix the spelling mistakes"
)

node.js:

const { Configuration, OpenAIApi } = require("openai");
const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);
const response = await openai.createEdit({
  model: "code-davinci-edit-001",
  input: "What day of the wek is it?",
  instruction: "Fix the spelling mistakes",
});

Parameters:

{
  "model": "code-davinci-edit-001",
  "input": "What day of the wek is it?",
  "instruction": "Fix the spelling mistakes",
}

Response:

{
  "object": "edit",
  "created": 1589478378,
  "choices": [
    {
      "text": "What day of the week is it?",
      "index": 0,
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 32,
    "total_tokens": 57
  }
}