No longer supported

This model is legacy (released June 2023) and is no longer actively maintained or recommended by OpenAI.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

legacyfastllm Proprietary

GPT-3.5-turbo-16k

by OpenAI· Released June 2023· Cutoff September 2021

GPT-3.5-turbo-16k is a variant of GPT-3.5-turbo with a 16,384-token context window, enabling processing of longer documents and conversations. It offers the same capabilities as GPT-3.5-turbo but with quadruple the context length. This model is optimized for chat and instruction-following tasks at a lower cost than GPT-4.

Official Site API Docs

Input cost

$0.003 per 1K tokens

Output cost

$0.004 per 1K tokens

Context window

16384 tokens

Max output

4096 tokens

Modalities

text

Parameters

175B

License

proprietary

Capabilities

Chat CompletionFunction CallingCode GenerationStreamingJSON ModeText SummarizationTranslation

Best For

Tasks requiring longer context, such as processing large documents or maintaining extended conversations.

Strengths

Larger context window (16K) compared to standard GPT-3.5-turbo
Cost-effective for long-context tasks
Fast inference speed
Good instruction following

Limitations

Legacy model, may be deprecated in the future
No vision or multimodal capabilities
Lower reasoning ability compared to GPT-4
Not suitable for tasks requiring very high accuracy

Use Cases

Long document summarization

Extended chatbot conversations

Code analysis of large codebases

Processing lengthy customer support transcripts

Analyzing long-form content like books or reports

Multi-turn dialogue with memory

Data extraction from large texts

Improvements Over Previous Model

Context window increased from 4K to 16K tokens compared to GPT-3.5-turbo
Same pricing per token as GPT-3.5-turbo despite larger context
Supports function calling (added in version 0613)
Improved instruction following over earlier GPT-3.5 versions
Lower latency than GPT-4 for long-context tasks

Back to all models