Models / openai / GPT-3.5 Turbo 16K

GPT-3.5 Turbo 16K

JSON →
openaillmdeprecated

An extended-context variant of GPT-3.5 Turbo supporting up to 16,384 tokens for longer conversations and documents.

textstreamingfunction-callingjson-modetool-useprompt-caching
homepage ↗docs ↗
Specs
Context & limits
16K
context window
4K
max output
Lifecycle
Dates
released2023-06-01
knowledge cutoff2021-09-01
deprecation2024-07-01
Resources
homepagehttps://platform.openai.com/docs/models/gpt-3-5-turbo ↗
docshttps://platform.openai.com/docs/api-reference/chat ↗