Last updated: 16/04/2025

OpenAIOfficial Docs

GPT-3.5 Turbo Instruct

gpt-3.5-turbo-instruct-0914

active

GPT-3.5 Turbo Instruct

GPT-3.5 Turbo Instruct is a legacy language model from OpenAI, designed for instruction-based tasks with a 4096 token context window. It supports a wide range of capabilities including text, image, video, audio, transcription, and text-to-speech, and can be fine-tuned for custom applications.

Supports a 4096 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Additional Information

Notes

This is the instruct variant of GPT-3.5 Turbo, designed for instruction-following use cases. According to the pricing information, it costs $1.50 per million tokens for input and $2.00 per million tokens for output.

Model Timeline

Launch Date

9/14/2023

Last Updated

9/14/2023

Knowledge Cutoff

4/1/2023

Capabilities

Text

Input Pricing

$1.50/ MTok

Context: 4,096 tokens

Output Pricing

$2.00/ MTok

Max tokens: 4,096

Transcription

Transcription Pricing

$0.006/minute

Text-to-Speech

Text-to-Speech Pricing

$0.01/1k characters

Embeddings

Embeddings Pricing

$0.0001/1k tokens

Fine-Tuning

Fine-Tuning Pricing

$8.00/MTok training

Additional Model Information

Tool Use

No

Structured Output

No

Reasoning

Yes

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop