GPT-5.2-Codex vs GPT-5.3 Chat (latest).

model vs model · prices as of

GPT-5.2-Codex takes 2 of 5 rounds against GPT-5.3 Chat (latest). It is also the cheaper of the two to run, at $17.80 per million tokens against $19.25.

OpenAIwins 2 rounds

GPT-5.2-Codex

$17.80/M tokens

cheapest we can explain, at Poe · $1.74 per 1,000 pages

400k context · tool calling · reads images

Poe
OpenAI

GPT-5.3 Chat (latest)

$19.25/M tokens

OpenAI list price, nothing below it is accounted for · $1.89 per 1,000 pages

128k context · tool calling · reads images

List price in (lower wins)

$1.75/M

$1.75/M

List price out (lower wins)

$14/M

$14/M

Cheapest we can explain (lower wins)

$17.80/M at Poe

none below list

Standard price (lower wins)

$19.25/M

$19.25/M

Cost per 1,000 pages (lower wins)

$1.74

$1.89

Context

400k tokens

128k tokens

Open weights

not stated

no

Tool calling

yes

yes

Structured output

yes

yes

Reads images

yes

yes

Reasoning

yes

no

Released

14 Jan 2026

3 Mar 2026

Providers selling it

22

6

Price we measure against

OpenRouter

the maker's own

Trains on your prompts (no is better)

not stated

no provider to check

Providers selling both · 2

  • Abacus$19.25 / $19.25
  • ZenMux$19.25 / $19.25

GPT-5.2-Codex then GPT-5.3 Chat (latest), per million tokens

Go further

Add a third or fourth model, or switch the weighting, in the tool.

What moved in the last seven days

  1. GPT-5.2-CodexNous Portal$1.40 / $11.20 $1.75 / $1425% dearer ·

Frequently asked

Which is cheaper, GPT-5.2-Codex or GPT-5.3 Chat (latest)?
GPT-5.2-Codex, at $17.80 per million tokens against $19.25 for GPT-5.3 Chat (latest), three parts input to one part output, read on 16 Sept 2026.
Where is each one cheapest?
GPT-5.2-Codex: $17.80 at Poe. GPT-5.3 Chat (latest): nobody goes below the maker's own price with a reason we can point at, so $19.25 is the number to beat.
Can I buy both from one provider?
Yes. 2 providers sell both: Abacus, ZenMux. The cheapest of them for the two together is Abacus.
Which holds more context?
GPT-5.2-Codex, at 400k tokens against 128k.

Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.

Related head-to-headsGPT-5.2-Codex vs GPT-5.3 CodexGPT-5.2-Codex vs Nova Premier 1.0GPT-5.2 vs GPT-5.2-CodexGPT-5.2 vs GPT-5.3 Chat (latest)GPT-5.3 Chat (latest) vs GPT-5.3 CodexMorecompare any two modelsevery model we track