GPT-5 vs GPT-5.1-Codex.

model vs model · prices as of

GPT-5.1-Codex takes 1 of 5 rounds against GPT-5. It is also the cheaper of the two to run, at $12.30 per million tokens against $12.50.

OpenAI

GPT-5

$12.50/M tokens

cheapest we can explain, at Poe · $1.23 per 1,000 pages

400k context · tool calling · reads images

Poe
OpenAIwins 1 rounds

GPT-5.1-Codex

$12.30/M tokens

cheapest we can explain, at Poe · $1.20 per 1,000 pages

400k context · tool calling · reads images

Poe

List price in (lower wins)

$1.25/M

$1.25/M

List price out (lower wins)

$10/M

$10/M

Cheapest we can explain (lower wins)

$12.50/M at Poe

$12.30/M at Poe

Standard price (lower wins)

$13.75/M

$13.75/M

Cost per 1,000 pages (lower wins)

$1.23

$1.20

Context

400k tokens

400k tokens

Open weights

no

not stated

Tool calling

yes

yes

Structured output

yes

yes

Reads images

yes

yes

Reasoning

yes

yes

Released

7 Aug 2025

13 Nov 2025

Providers selling it

33

19

Price we measure against

the maker's own

OpenRouter

Trains on your prompts (no is better)

not stated

not stated

Providers selling both · 16

  • Poe$12.50 / $12.30
  • Jiekou$13.06 / $13.06
  • Abacus$13.75 / $13.75
  • Azure AI Foundry$13.75 / $13.75
  • Azure Cognitive Services$13.75 / $13.75
  • Helicone$13.75 / $13.75
  • Impossibl$13.75 / $13.75
  • Kilo Gateway$13.75 / $13.75

GPT-5 then GPT-5.1-Codex, per million tokens · showing the 8 cheapest of 16

Go further

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

What moved in the last seven days

  1. GPT-5Nous Portal$1 / $8 $1.25 / $1025% dearer ·
  2. GPT-5Requesty$1.25 / $10 $1.38 / $1110% dearer ·
  3. GPT-5.1-CodexNous Portal$1 / $8 $1.25 / $1025% dearer ·

Frequently asked

Which is cheaper, GPT-5 or GPT-5.1-Codex?
GPT-5.1-Codex, at $12.30 per million tokens against $12.50 for GPT-5, three parts input to one part output, read on 16 Sept 2026.
Where is each one cheapest?
GPT-5: $12.50 at Poe. GPT-5.1-Codex: $12.30 at Poe.
Can I buy both from one provider?
Yes. 16 providers sell both: Poe, Jiekou, Abacus, Azure AI Foundry, Azure Cognitive Services, Helicone, and more. The cheapest of them for the two together is Poe.
Which holds more context?
Both hold 400k tokens in one call.

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-headsGemini 2.5 Computer Use Preview 10-2025 vs GPT-5Gemini 2.5 Computer Use Preview 10-2025 vs GPT-5.1-CodexGemini 2.5 Pro vs GPT-5Gemini 2.5 Pro vs GPT-5.1-CodexGPT-5 vs GPT-5.1GPT-5 vs GPT-5.1-Codex-MaxMorecompare any two modelsevery model we track