Logo
Back to all models

davinci-002 - In-Depth Overview

OpenAI · GPT-3

outdated

Model ID: davinci-002

Get all the details on davinci-002, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as fine_tuning, available API code samples, and performance strengths.

Key Metrics

Input Limit

No data tokens

Output Limit

16.4K tokens

Input Cost

$2.00/1M

Output Cost

$2.00/1M

Sample API Code

import openai

client = openai.OpenAI()

response = client.completions.create(
  model="davinci-002",
  prompt="Say this is a test",
  max_tokens=7,
  temperature=0
)
print(response.choices[0].text)

Required Libraries

openai
openai

Notes

GPT base models can understand and generate natural language or code but are not trained with instruction following. These models are made to be replacements for our original GPT-3 base models and use the legacy Completions API. Most customers should use GPT-3.5 or GPT-4.

Capabilities

Supported Data Types

Input Types

text

Output Types

text

Strengths & Weaknesses

Good at

natural language understanding
natural language generation
code generation

Poor at

instruction following
streaming
function calling
structured outputs
web browsing

Additional Information

Latest Update

Sep 1, 2021

Knowledge Cutoff

Sep 1, 2021