GPT-3.5 Turbo 16k chat
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.
Capabilities
Context Window 16k tokens
Max Output 4k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $3.00
Output $4.00
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p