Verified October 2026

Home › Models › GPT-5.2

GPT-5.2 API pricing

GPT-5.2 is a model from OpenAI with a 400,000-token context window. Rates below are per 1,000,000 tokens, verified October 2026.

$1.75Input / 1M tokens
$14Output / 1M tokens
$0.175Cached input / 1M
400,000Context window

Price list

GPT-5.2 rates in USD per 1M tokens, October 2026
Token classRate / 1MNotes
Input$1.75Prompt tokens not served from cache
Cached input$0.17590% below base input
Cache write—Not billed per token
Output$148.0× the input rate
Batch API−50%Input and output, results within 24 h

What GPT-5.2 costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$15.40
RAG with caching1,00050K in (45K cached) / 1K out$30.70
Nightly batch job10,00010K in / 2K out$228

Caching the 45K-token prefix saves about 70% on the RAG workload versus sending it uncached every call ($102 → $30.70). Batch mode halves the nightly job.

Where GPT-5.2 sits in the market

Out of 28 models in this dataset, GPT-5.2 ranks #14 cheapest by input rate, #21 by output rate, and #21 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
GPT-5.2OpenAI$1.75$14$5.25
Gemini 3.1 Pro (Preview)Google Gemini$2$12$5
GPT-5.4OpenAI$2.50$15$6.25
GPT-5.6 TerraOpenAI$2$12$5

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does GPT-5.2 cost per 1M tokens?

$1.75 per 1M input tokens and $14 per 1M output tokens on the standard tier.

Is prompt caching cheaper on GPT-5.2?

Yes. Cached input bills at $0.175 per 1M tokens, 90.0% below the $1.75 base input rate, with no separate cache-write rate published.

Does GPT-5.2 support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $455 at list price and about $228 in batch mode.

Keep reading

Run these numbers in the calculator