Skip to content
LLMs
OpenAI logo

OpenAI: GPT-3.5 Turbo 16k

by OpenAI

OpenAI: GPT-3.5 Turbo 16k is a large language model from OpenAI. It costs $3.00 per million input tokens and $4.00 per million output tokens. Its context window is 16K tokens.

Tool callingStructured output
Input / 1M tokens
$3.00
Output / 1M tokens
$4.00
Cached input / 1M
-

Not supported

Context window
16K

tokens

Who serves it cheapest

2 hosts serve GPT-3.5 Turbo 16k. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-3.5 Turbo 16k, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AzureCheapest$3.00$4.0016K-100.0%
OpenAI$3.00$4.0016K-100.0%

The spread between Azure and OpenAI is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

About GPT-3.5 Turbo 16k

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

Specifications

OpenAI: GPT-3.5 Turbo 16k specifications
Model IDopenai/gpt-3.5-turbo-16k
ProviderOpenAI
Context window16K tokens
Max output4K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2021-09-30
Open weightsNo
ReleasedAugust 28, 2023

Cheaper alternatives

Models that cost less than GPT-3.5 Turbo 16k while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does OpenAI: GPT-3.5 Turbo 16k cost?

$3.00 per million input tokens and $4.00 per million output tokens.

What is the context window of OpenAI: GPT-3.5 Turbo 16k?

16K tokens, with up to 4K tokens of output per request.

Which provider serves OpenAI: GPT-3.5 Turbo 16k cheapest?

Azure at $3.00 per million input tokens - about the same cheaper than OpenAI, the most expensive of the 2 hosts serving it.

Confirm against the source: OpenAI official pricing.