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
- Hardest reasoning benchmarks where the gap to base 5.2 is measurable and meaningful.
- Single-shot answers to expensive-to-recover-from questions, legal drafts, executive memos, high-stakes code reviews.
- Eval ceiling testing, when you want to know "what's the best this family can do" on a specific task.
When not to use it:
- Anywhere base GPT-5.2 ($1.75/$14) hits your accuracy bar. Run the eval first.
- High-volume workloads, 12× costs at scale.
- Tasks better suited to o3-pro ($20/$80) which is positioned for explicit reasoning at lower output rate.
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
- GPT-5.5 (OpenAI, $5.00/$30.00)
- GPT-5.5 Pro (OpenAI, $30.00/$180.00)
- GPT-5.4 (OpenAI, $2.50/$15.00)
- GPT-5.4 Mini (OpenAI, $0.75/$4.50)
- GPT-5.4 Nano (OpenAI, $0.20/$1.25)
- GPT-5.4 Pro (OpenAI, $30.00/$180.00)
- GPT-5.3 (OpenAI, $1.75/$14.00)
- GPT-5.2 (OpenAI, $1.75/$14.00)
- GPT-5.1 (OpenAI, $1.25/$10.00)
- GPT-5 (OpenAI, $1.25/$10.00)
- GPT-5 Mini (OpenAI, $0.25/$2.00)
- GPT-5 Nano (OpenAI, $0.05/$0.40)
- GPT-5 Pro (OpenAI, $15.00/$120.00)
- GPT-4.1 (OpenAI, $2.00/$8.00)
- GPT-4.1 Mini (OpenAI, $0.40/$1.60)
- GPT-4.1 Nano (OpenAI, $0.10/$0.40)
- o3 (OpenAI, $2.00/$8.00)
- o3-mini (OpenAI, $1.10/$4.40)
- o3-pro (OpenAI, $20.00/$80.00)
- o4-mini (OpenAI, $1.10/$4.40)
- GPT-4o (OpenAI, $2.50/$10.00)
- GPT-4o mini (OpenAI, $0.15/$0.60)
- GPT-4 Turbo (OpenAI, $10.00/$30.00)
- Claude Opus 4.8 (Fast Mode) (Anthropic, $10.00/$50.00)
- Claude Opus 4.8 (Anthropic, $5.00/$25.00)
- Llama 3.1 405B (Meta, $3.50/$3.50)