OpenAI: GPT-3.5 Turbo 16k

Text input Text output Unavailable
Author's Description

The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Sep 2021. This version has a higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

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

This model supports the following parameters:

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

This model supports the following features:

Response Format Tools
Performance Summary

OpenAI's GPT-3.5 Turbo 16k, released on May 27, 2023, demonstrates a strong overall performance profile, particularly excelling in operational efficiency. This model consistently ranks among the fastest available, achieving the 98th percentile in speed across benchmarks. It also offers competitive pricing, positioned at the 57th percentile. A standout feature is its exceptional reliability, boasting a perfect 100th percentile, indicating minimal technical failures and consistent response delivery. The model incorporates significant improvements, including enhanced instruction following, JSON mode, reproducible outputs, and parallel function calling, alongside a fix for non-English language function call encoding issues. While its Reasoning (Baseline) benchmark shows 48.0% accuracy (34th percentile), suggesting room for improvement in complex multi-step reasoning tasks, its high speed and reliability make it a robust choice for applications prioritizing consistent and rapid output generation. Its training data extends up to September 2021.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.5
Completion $1.5

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-3.5-turbo-0125 16K $0.5 / 1M tokens $1.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by openai