OpenAI

GPT-3.5 Turbo Instruct

by OpenAItext->text1 endpoint

Overview

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

Capabilities

Text generation
Structured output
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
4.1K tokens
Max Output
3.7K tokens
Knowledge Cutoff
2021-09-30
Tokenizer
GPT
Content Moderation
Enabled
Uptime (24h)
10000.0%

Supported Parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_logprobstop_p

Pricing

Per 1M tokens
Input$1.50
Output$2.00
Added
September 28, 2023
Last synced 9/18/2026