GPT-3.5 Turbo 16k pricing.

Prices checked

GPT-3.5 Turbo 16k costs $3 in and $4 out per million tokens from OpenAI; the cheapest price is $3.25 at OpenRouter, checked .

OpenAI's own price

OpenAI

$3.25/M tokens

$3 in · $4 out

269% above the typical price of the 392 text models we track.

Cheapest price

OpenRouter

$3.25/M tokens

$3 in · $4 out

Nobody sells it for less than OpenAI with a reason we can point at.

Web search from this model costs $10 per 1,000 searches, plus its tokens; dedicated search APIs from $1

tool callingstructured output16k contextreleased 28 Aug 2023

Every provider selling GPT-3.5 Turbo 16k

  1. 1

    OpenRouter

    Same as maker

    $3 in · $4 out

    $3.25/M tokens
  2. 2

    Kilo Gateway

    Same as maker

    $3 in · $4 out

    $3.25/M tokens
  3. 3

    OpenAI

    Maker's price

    $3 in · $4 out

    $3.25/M tokens
  4. 4

    Azure AI Foundry

    Same as maker

    $3 in · $4 out

    $3.25/M tokens
  5. 5

    Nous Portal

    Same as maker

    $3 in · $4 out

    $3.25/M tokens
  6. 6

    FastRouter

    Same as maker

    $3 in · $4 out

    $3.25/M tokens

Something else wrong?

What it costs for your work
pages a month
$2.04

A month at OpenAI's own price

$2.04

A month at OpenRouter, the cheapest

$0

What you save

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

How we count

Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenAI's own is listed as cheapest only when the provider says why.

Same as maker
Sold by someone else at the price the maker charges.
Maker's price
What the lab that trained the model charges on its own API. Every other row is measured against it.

Similar models

Models from other labs that do what GPT-3.5 Turbo 16k does, cheapest first. Each percentage is against GPT-3.5 Turbo 16k's cheapest price, $3.25 per M tokens.

Frequently asked

Who sells GPT-3.5 Turbo 16k cheapest?
No provider sells GPT-3.5 Turbo 16k below OpenAI's own price for a reason it publishes. 6 providers sell it at that price or above, and every one of them is on this page.
Is GPT-3.5 Turbo 16k open weights?
No. OpenAI keeps the weights, so every price on this page is OpenAI's own or a resale of it. A price below OpenAI's here needs a published reason, or it is listed and not ranked.
How much context does GPT-3.5 Turbo 16k hold?
16,385 tokens in one call, which is about 16k, and it can call your own functions.
How does GPT-3.5 Turbo 16k compare with the rest of the market?
At $3.25 per million tokens, OpenAI's own price is 269% above the typical $0.88 across the 392 text models we track.

More from OpenAI