Back to all models
Get all the details on GPT-3.5 Turbo Instruct, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as instruction_following, available API code samples, and performance strengths.
Key Metrics
Input Limit
4.1K tokens
Output Limit
4.1K tokens
Input Cost
$1.50/1M
Output Cost
$2.00/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
completion = client.completions.create(
model="gpt-3.5-turbo-instruct",
prompt="Write a short story about a robot dog.",
max_tokens=50
)
print(completion.choices[0].text)Required Libraries
openai
openai
Notes
An older model only compatible with the legacy Completions endpoint. Similar capabilities as GPT-3 era models.
Capabilities
instruction following
Supported Data Types
Input Types
text
Output Types
text
Strengths & Weaknesses
Good at
text generation
instruction following
Poor at
complex reasoning
multimodal tasks
long context
Additional Information
Latest Update
Sep 1, 2021
Knowledge Cutoff
Sep 1, 2021