GPT-4 Turbo Preview (0125)
JSON →GPT-4 Turbo preview snapshot from January 2024 with reduced 'laziness' and improved task completion.
Specs
context window 128K tokens
max output 4K tokens
input price $10 / 1M tokens
output price $30 / 1M tokens
Capabilities
tool-usejson-modestreamingfunction-callingprompt-caching
Dates
releasedJan 2024
knowledge cutoffApr 2023
deprecatedApr 2024
Resources
API
full doc /v1/models/gpt-4-0125-preview