AI Calculator Pro

GPT-5.2 Codex

OpenAI · model · context window 400,000 tokens.

Pricing (per 1M tokens)

Input$1.75
Output$14.00
Cache read$0.1750

Specifications

Context window400,000 tokens
Max output128,000 tokens
Modalitiestext
VisionNo
Tool useYes
ReasoningNo
Prompt cachingNo

Intelligence & value

Measured
Coding1334 · #72

Worth it? GPT-5.2 Codex is on the price/quality frontier — nothing we track matches its overall Arena score for less. If you can accept a small quality drop, the downgrade calculator finds cheaper options.

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 18 September 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

Where else you can run GPT-5.2 Codex

The same model is resold by 20 providers we track. The typical one charges 12.3× what the cheapest does — $4.81 against $0.3900 per 1M tokens, blended 3:1. Routing the same workload to a different host is often a bigger saving than switching model.

ProviderInput / 1MOutput / 1MBlended
Qihang AI$0.1400$1.14$0.3900
Ofox$1.40$11.20$3.85
Poe$1.60$13.00$4.45
Abacus$1.75$14.00$4.81
Aihubmix$1.75$14.00$4.81
Azure$1.75$14.00$4.81
Azure Cognitive Services$1.75$14.00$4.81
Edenai$1.75$14.00$4.81
Impossibl$1.75$14.00$4.81
Jiekou$1.75$14.00$4.81

Showing the 10 cheapest of 20. The full list for every model is in the open endpoint dataset.

Third-party listings via models.dev, not rates we verify with each host the way we do first-party pricing. Treat them as a shortlist to check, not a quote — and confirm quantisation, context limits and rate limits before switching, since a cheaper host is not always serving the same thing.

Estimate cost with GPT-5.2 Codex

GPT-5.2 Codex is pre-selected below. Enter your token counts and volume to see the cost per request, per day and per month — then switch models to compare.

Results update automatically as you type.

Result
$0.00875 per request
~$262.50/month at 1,000 requests/day
Input cost
$0.00175
Output cost
$0.00700
Per request
$0.00875
Per day
$8.75
Per month
$262.50

Source: auto-discovery (models.dev). Prices are re-checked daily against the provider’s official pricing; this rate was last changed on 19 July 2026. A recent date here just means the price is still current, not that it moved.