Skip to content

Interface language: EN. Editorial content: German. Prices refer to Germany.

Sir CompareComparisons with evidenceAsk Sir CompareAsk
Germany · EUR
Country and pricesUnited KingdomGBPUnited StatesUSDItalyEURGermanyEURSpainEURFranceEUR
Language: English
ITENDEFRES

Product

GPT-5.3-Codex: Datenblatt, API-Preise und Daten

Updated

OpenAI gpt-5.3-codex — drawn card, not a photograph of the product

OpenAIAI Models & LLMs

Context window
400k tokens
Maximum output
128k tokens
Input cost per 1M tokens
$1.75
Output cost per 1M tokens
$14.00
Knowledge cutoff
August 2025

You use it and pay per use through the vendor's API, per million tokens: there is no shop. The list prices are in the data sheet below.

Official page: developers.openai.com ↗

Data sheet · GPT-5.3-Codex

Every figure is quoted from the vendor's official page, with the date we read it. If a row is missing, the source does not state it and we do not estimate it.

Memory and answer length

Context window
400k tokensRank 18 of 21
What it means and the source

How much text the model keeps in view in a single request, question and answer included. It matters for long documents and whole code projects. A token is a fragment of a word.

developers.openai.comOpens the source in a new tab Oct 23, 2026
Maximum output
128k tokensRank 3 of 16
What it means and the source

The longest answer it can write in one go: useful for reports, long code or translations of whole documents.

developers.openai.comOpens the source in a new tab Oct 23, 2026

API prices

Input cost per 1M tokens
$1.75Rank 10 of 21
What it means and the source

What it costs to have the model read a million tokens (your question, the documents, the code). It is the official list price, before discounts.

developers.openai.comOpens the source in a new tab Oct 23, 2026
Cached input cost per 1M tokens
$0.175Rank 11 of 20
What it means and the source

The reduced price when part of the request is identical to one sent recently, for example the same instructions or the same document: the vendor keeps it in memory and charges less for it.

developers.openai.comOpens the source in a new tab Oct 23, 2026
Output cost per 1M tokens
$14.00Rank 14 of 21
What it means and the source

What a million tokens written by the model cost. It usually costs more than the input and is the figure to watch when answers are long.

developers.openai.comOpens the source in a new tab Oct 23, 2026

Knowledge and abilities

Knowledge cutoff
August 2025Rank 9 of 9
What it means and the source

The month up to which the model's knowledge reaches. For more recent facts it needs web search or your documents.

developers.openai.comOpens the source in a new tab Oct 23, 2026
Reads images
Yes13 models out of 23
What it means and the source

The model can take images (photos, screenshots, charts) as well as text.

developers.openai.comOpens the source in a new tab Oct 23, 2026

Where it stands · GPT-5.3-Codex

The same verified figures, next to those of the other catalogue models. Tap a model for the head-to-head.

Context windowRank 18 of 21 · higher is better
  1. 1GPT-5.6 Sol1.05M tokens
  2. 1GPT-6 Astra1.05M tokens
  3. 1GPT-6 Luna1.05M tokens
  4. 1GPT-6.1 Sol1.05M tokens
  5. 5Gemini 3.8 Flash1,048,576 tokens
  6. 18GPT-5.3-Codex400k tokens
Maximum outputRank 3 of 16 · higher is better
  1. 1DeepSeek V4 Pro384k tokens
  2. 1DeepSeek V4.1 Flash384k tokens
  3. 3GPT-5.3-Codex128k tokens
  4. 3Claude Fable 5.1128k tokens
  5. 3Claude Haiku 5.5128k tokens
  6. 3Claude Opus 5.5128k tokens
Input cost per 1M tokensRank 10 of 21 · lower is better
  1. 1Claude Haiku 5.5$0.10
  2. 1GPT-6 Luna$0.10
  3. 3DeepSeek V4.1 Flash$0.30
  4. 4GLM-4.6$0.60
  5. 5Gemini 3.8 Flash$0.75
  6. 10GPT-5.3-Codex$1.75
Output cost per 1M tokensRank 14 of 21 · lower is better
  1. 1Claude Haiku 5.5$0.50
  2. 1GPT-6 Luna$0.50
  3. 3DeepSeek V4.1 Flash$1.20
  4. 4GLM-4.6$2.20
  5. 5GLM-5$3.20
  6. 14GPT-5.3-Codex$14.00

Questions and answers

GPT-5.3-Codex: how much does it cost through the API?

The official list price is $1.75 per 1M input tokens and $14.00 per 1M output tokens.

GPT-5.3-Codex: how much text can it read at once?

The context window is 400k tokens. It can write answers of up to 128k tokens.

GPT-5.3-Codex: how recent is its knowledge?

Its knowledge reaches August 2025. For more recent facts it needs web search or your documents.

Kurz gefasst

Bei OpenAI GPT-5.3-Codex ist Kontextfenster der Wert, auf den es ankommt: 400,000. Ich habe sie von OpenAI – GPT-5.3-Codex übernommen. Unter den 21, die ich geprüft habe, sind 17 besser. Die andere Zahl, auf die es ankommt, ist Kosten pro 1 Mio. Ausgabe-Token: 14.

Die Zahlen zu OpenAI GPT-5.3-Codex

Ich habe sie nach Gewicht geordnet, mit dem Wert und dem Platz unter den anderen, die ich geprüft habe.

Kontextfenster: 400,000. Platz 18 von 21, die ich verglichen habe.

Kosten pro 1 Mio. Ausgabe-Token: 14. Platz 14 von 21, die ich verglichen habe.

Kosten pro 1 Mio. Eingabe-Token: 1.75. Platz 10 von 21, die ich verglichen habe.

Kosten für Cache-Eingabe pro 1 Mio. Token (USD): 0.175. Platz 10 von 20, die ich verglichen habe.

Liest Bilder: 1. Das ist der beste Wert unter den 13, die ich verglichen habe.

Maximale Antwort (k Token): 128,000. Platz 3 von 16, die ich verglichen habe.

Subject illustration: Illustration of an application (illustrative image, not a photo of the product)
Für wen es sich lohnt

Nimm es, wenn Liest Bilder für dich Vorrang hat: 1 — keines der geprüften Modelle ist besser.

Sieh dich anderswo um, wenn dir Kontextfenster wichtig ist: hier sind es 400,000, und 17 Produkte sind besser.

Verwandte Inhalte

Quellen

Ask Sir Compare:Explain these numbers to me

Reviews and tests

OpenAI GPT-5.3-Codex

Reviews and tests · OpenAI GPT-5.3-Codex

Reviews are not available yet.

What changed

  • Page updated

How I put products in order

Sir Compare’s letter

Updates on AI Models & LLMs? I’ll send them your way.

Pick what you care about: I only write when something new comes out — a guide, a news story, a verified price that drops.

Step 1 of 2

What are you into?

Pick as many as you like. Pick none and you get what’s new in every section.

What you want to receive
  • Only what you pick
  • Never an empty email
  • One click to leave

Your assistant

Open full page →