Back to all models
Get all the details on GPT-3.5 Turbo (0125), an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as function_calling, json_mode, available API code samples, and performance strengths.
Key Metrics
Input Limit
16.4K tokens
Output Limit
4.1K tokens
Input Cost
$0.50/1M
Output Cost
$1.50/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-3.5-turbo-0125",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Required Libraries
openai
openai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1106 | lmarena.ai | - | |
53.95 | LiveBench | Score for GPT-3.5 Turbo family | |
39.75 | LiveBench | Score for GPT-3.5 Turbo family | |
69.29 | LiveBench | Score for GPT-3.5 Turbo family | |
41.48 | LiveBench | Score for GPT-3.5 Turbo family | |
63.53 | LiveBench | Score for GPT-3.5 Turbo family | |
44.68 | LiveBench | Score for GPT-3.5 Turbo family | |
64.94 | LiveBench | Score for GPT-3.5 Turbo family |
Notes
A legacy model in the GPT-3.5 family, suitable for cheaper chat and non-chat tasks. It is not the latest or flagship model.
Capabilities
function calling
json mode
Supported Data Types
Input Types
text
Output Types
text
json
Strengths & Weaknesses
Good at
General text generation
Chat
Cost-effectiveness for basic tasks
Poor at
Complex reasoning
Multimodal tasks
Handling very long contexts
Additional Information
Latest Update
Jan 25, 2025
Knowledge Cutoff
Jun 1, 2024