GPT-3.5 Turbo (0125)
JSON →Updated GPT-3.5 Turbo snapshot from January 2025 with improved accuracy and lower pricing.
Specs
context window 16K tokens
max output 4K tokens
input price $0.5 / 1M tokens
output price $1.5 / 1M tokens
Capabilities
tool-usejson-modestreamingfunction-callingprompt-caching
Dates
releasedJan 2025
knowledge cutoffSep 2021
Resources
API
full doc /v1/models/gpt-3.5-turbo-0125