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
Refer to official OpenAI documentation.Required Libraries
openai
openai
Notes
Snapshot of GPT-3.5 Turbo (version 0125). Optimized for chat using the Chat Completions API. Currently the version pointed to by the 'gpt-3.5-turbo' alias. The 'Features' table on this page states it lacks streaming, function calling, and structured outputs, while supporting fine-tuning. Context window: 16,385 tokens, Max output tokens: 4,096.
Capabilities
natural language understanding
code generation
chat
non-chat tasks
fine-tuning
Supported Data Types
Input Types
Text
Output Types
Text
Strengths & Weaknesses
Good at
natural language understanding
code generation
chat tasks
non-chat tasks
fine-tuning
cost-effectiveness (historically)
Poor at
relatively lower intelligence (compared to newer models)
relatively slower speed (compared to newer models)
lacks streaming (per this document)
lacks function calling (per this document)
lacks structured outputs (per this document)
Additional Information
Latest Update
Jan 25, 2024
Knowledge Cutoff
2021-09-01