No longer supported

This model is legacy (released November 2023) and is no longer actively maintained or recommended by OpenAI. Consider using their current flagship model instead.

legacylegacyllm Proprietary

GPT-3.5-turbo-instruct

by OpenAI· Released November 2023· Cutoff September 2021

GPT-3.5-turbo-instruct is a legacy model from OpenAI that combines the capabilities of the older InstructGPT with the efficiency of GPT-3.5-turbo. It is designed for instruction-following tasks and offers a balance of performance and cost. This model is being phased out in favor of newer models like GPT-4o-mini.

Official Site API Docs

Input cost

$1.50 per 1M tokens

Output cost

$2.00 per 1M tokens

Context window

4096 tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationInstruction FollowingCode GenerationStreaming

Best For

Simple instruction-following tasks and code generation where cost efficiency is key.

Strengths

Cost-effective for high-volume tasks
Good at following explicit instructions
Supports streaming for real-time applications

Limitations

Smaller context window (4K tokens)
No vision or multimodal capabilities
Legacy status with limited support
Lower performance compared to newer models

Use Cases

Chatbots and virtual assistants

Code generation and completion

Content summarization

Data extraction and formatting

Question answering

Text classification

Language translation

Improvements Over Previous Model

Introduced as a replacement for the older InstructGPT models
Lower latency compared to GPT-3.5-turbo for non-chat completions
Simplified API with a single prompt input
Pricing reduced compared to previous instruct models

Back to all models

No longer supported

This model is legacy (released November 2023) and is no longer actively maintained or recommended by OpenAI. Consider using their current flagship model instead.

legacylegacyllm Proprietary

GPT-3.5-turbo-instruct

by OpenAI· Released November 2023· Cutoff September 2021

Official Site API Docs

Input cost

$1.50 per 1M tokens

Output cost

$2.00 per 1M tokens

Context window

4096 tokens

Max output

4096 tokens

Modalities

text

License

proprietary

Capabilities

Text GenerationInstruction FollowingCode GenerationStreaming

Best For

Simple instruction-following tasks and code generation where cost efficiency is key.

Strengths

Cost-effective for high-volume tasks
Good at following explicit instructions
Supports streaming for real-time applications

Limitations

Smaller context window (4K tokens)
No vision or multimodal capabilities
Legacy status with limited support
Lower performance compared to newer models

Use Cases

Chatbots and virtual assistants

Code generation and completion

Content summarization

Data extraction and formatting

Question answering

Text classification

Language translation

Improvements Over Previous Model

Introduced as a replacement for the older InstructGPT models
Lower latency compared to GPT-3.5-turbo for non-chat completions
Simplified API with a single prompt input
Pricing reduced compared to previous instruct models

Back to all models