#tHow Many Tokens?

← All models

GPT-5.2 Pro: token counter & pricing

OpenAI · exact (uses official tokenizer) · pricing as of 2026-05-31.

Provider
OpenAI
API model ID
gpt-5.2-pro
Context window
400,000 tokens
Input price
$21.00 per 1M tokens
Output price
$168.00 per 1M tokens
Tokenizer accuracy
exact (uses official tokenizer)
Pricing as of
2026-05-31

Open the counter to count tokens for GPT-5.2 Pro in real time.

What is GPT-5.2 Pro?

GPT-5.2 Pro is the premium reasoning tier of OpenAI's GPT-5.2 model, same tokenizer and context window, dramatically more reasoning capacity, dramatically higher price. $21 input / $168 output per 1M tokens, 12× the base GPT-5.2 input rate, 12× the output rate.

This is for tasks where you have measured base GPT-5.2 falling short and the cost of a wrong answer outweighs the 12× per-call markup.

How tokens are counted here

OpenAI's o200k_base tokenizer (same as the entire GPT-5 family). Browser-side via js-tiktoken. Exact.

Pricing notes

$21 input / $168 output per 1M. No cached-input rate listed, Pro tier doesn't qualify for OpenAI's caching discount today.

For a 1,000-token prompt with a 200-token reply: $0.0546 per call, ~$54,600 per 1M calls. That's 24× more expensive than base GPT-5.2 ($2,275/M) at this ratio, and 1,000× more expensive than GPT-5 Nano ($55/M) which is OpenAI's cheap tier with the same tokenizer.

When to use GPT-5.2 Pro

When not to use it:

Common questions

Is GPT-5.2 Pro worth it over o3-pro?

o3-pro is $20/$80, 49% cheaper on output. o3-pro bills you for invisible reasoning tokens (typical 5-15× output overhead), so real-world cost gap narrows. Run both on your hardest evals; if neither wins decisively, default to o3-pro for cost.

Same context window as base GPT-5.2?

Yes, 400K input. Same long-context behavior.

When did OpenAI release Pro tiers?

Pro tiers across the GPT-5 family (5, 5.2, 5.4, 5.5) all priced near the same premium ($15-$30 input), positioned to capture workloads previously running on Claude Opus or expensive third-party reasoning APIs.

Compare GPT-5.2 Pro to other models