OpenAI: GPT-3.5 Turbo 16k

Text input Text output
Author's Description

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...

Key Specifications
Cost
$$$$$
Context
16K
Parameters
175B
Released
Aug 27, 2023
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tools Response Format Top Logprobs Stop Frequency Penalty Logprobs Tool Choice Temperature Max Tokens Structured Outputs Presence Penalty Logit Bias Top P Seed
Features

This model supports the following features:

Structured Outputs Tools Response Format
Performance Summary

OpenAI's GPT-3.5 Turbo 16k, released on August 27, 2023, distinguishes itself with a significantly extended context length of 16385 tokens, four times that of its predecessor, enabling it to process approximately 20 pages of text per request. This model consistently ranks among the fastest available, achieving the 96th percentile in speed across two benchmarks. While its pricing is moderate, falling into the 21st percentile, its reliability is exceptional, demonstrating a perfect 100% success rate across two benchmarks, indicating minimal technical failures. In benchmark performance, GPT-3.5 Turbo 16k achieved 95.5% accuracy in General Knowledge, placing it in the 37th percentile, with a cost of $0.1647 (21st percentile) and a duration of 151465ms (95th percentile). For Ethics, it scored 99.0% accuracy (49th percentile), with a cost of $0.1110 (22nd percentile) and a duration of 85053ms (97th percentile). Its key strengths lie in its high speed, outstanding reliability, and expanded context window, making it suitable for complex, long-form tasks. A notable weakness is its accuracy in General Knowledge, which, while high, is not top-tier compared to other models.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $3
Completion $4

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-3.5-turbo-16k 16K $3 / 1M tokens $4 / 1M tokens
Azure
Azure | openai/gpt-3.5-turbo-16k 16K $3 / 1M tokens $4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai