Compact GPT model for low-latency assistance and high-volume workloads

Details

FieldValue
idopenai/gpt-4-turbo-preview
familygpt
modalitytext+pdf->text
context_length128000
max_output_tokens4096
release_date2024-01-25
is_open_weightsno
supports_tool_callyes
supports_reasoningno
supports_structured_outputyes
supports_attachmentyes
input_modalitiestext, pdf
output_modalitiestext

Providers