OpenAI: GPT-3.5 Turbo 16k

Public pricingIntelligence 76/100Small memoryTool use

OpenAI: GPT-3.5 Turbo 16k is a text model for general chat, analysis, and production use. It combines steady general-purpose performance with a 16K tokens context window and a premium profile. Use it for general chat, analysis, and production workloads when quality, speed, and cost matters.

Input

$3.00/1M

Output

$4.00/1M

Cached

$0.30/1M

Batch

$1.50/1M

Calculate your GPT-3.5 Turbo 16k bill.

Set your workload — see cost at your exact volume.

What would GPT-3.5 Turbo 16k cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

GPT-3.5 Turbo 16k at a glance.

Memory

16,385

tokens

Max reply

4,096

tokens

Memory tier

Small

a few emails or a short document

Tokenizer

tiktoken-o200k

Released

Jun 2023

Training cutoff

Sep 2021

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • mmlu

    70

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick GPT-3.5 Turbo 16k

  • Agentic workflows that call tools or APIs.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.
  • Your inputs routinely exceed short documents.

Alternatives

Similar models to compare.

FAQ

GPT-3.5 Turbo 16k — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, GPT-3.5 Turbo 16k costs roughly $385 per month. Input is $3.00 /1M tokens and output is $4.00 /1M tokens.
GPT-3.5 Turbo 16k has a 16,385-token context window (small memory — a few emails or a short document). That means you can fit about 3,072 words of input and history in a single call.
Beyond text generation, GPT-3.5 Turbo 16k supports calling functions / tools, strict JSON output. It streams replies by default.
GPT-3.5 Turbo 16k was released in June 2023, with training data cut off around September 2021.
Models in a similar class include GPT Audio, GPT-4o (2024-11-20), GPT-4o Audio. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare GPT-3.5 Turbo 16k against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard