
GPT-3.5-turbo
openai/gpt-3.5-turbo
Compact GPT model for low-latency assistance and high-volume workloads
Capabilities
ReasoningNo
Tool callingNo
Structured outputNo
TemperatureSupported
AttachmentNo
Open weightsNo
Limits
Context16,385 tokens
Max inputN/A
Max output4,096 tokens
Details
Familygpt
Knowledge cutoff2021-09-01
Release date2023-03-01
Last updated2023-11-06
Benchmarks
Artificial Analysis Coding Index
10.7
index
Comments (0)
Sign in to leave a comment
No comments yet.