Back to all models
Get all the details on babbage-002, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as Code Generation, code_understanding, text_generation, available API code samples, and performance strengths.
Key Metrics
Input Limit
16.4K tokens
Output Limit
16.4K tokens
Input Cost
$0.40/1M
Output Cost
$0.40/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
response = client.completions.create(
model="babbage-002",
prompt="Write a short story about a robot.",
max_tokens=100
)
print(response.choices[0].text)Required Libraries
openai
openai
Notes
Replacement for the GPT-3 ada and babbage base models. Uses the legacy Completions API. Not trained with instruction following. Most customers should use GPT-3.5 or GPT-4.
Capabilities
Code Generation
code understanding
text generation
text understanding
Supported Data Types
Input Types
text
Output Types
text
Strengths & Weaknesses
Good at
text generation
code generation
Poor at
instruction following
complex reasoning
multimodal tasks
function calling
structured outputs
Additional Information
Latest Update
Jun 1, 2023
Knowledge Cutoff
Sep 1, 2021