#tHow Many Tokens?

← All models

GPT-5.5 Pro: token counter & pricing

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

Provider
OpenAI
API model ID
gpt-5.5-pro
Context window
400,000 tokens
Input price
$30.00 per 1M tokens
Output price
$180.00 per 1M tokens
Tokenizer accuracy
exact (uses official tokenizer)
Pricing as of
2026-05-31

Open the counter to count tokens for GPT-5.5 Pro in real time.

What is GPT-5.5 Pro?

GPT-5.5 Pro is OpenAI's current top-tier reasoning model, the Pro variant of the flagship GPT-5.5. Same o200k_base tokenizer, same 400K context, dramatically higher reasoning capacity and price. $30 input / $180 output per 1M tokens, 6× the base 5.5 input rate, 6× the output rate.

If GPT-5.5 ($5/$30) is the production default, GPT-5.5 Pro is what you reach for when base 5.5 measurably falls short on a specific eval and the per-call cost is justified.

How tokens are counted here

OpenAI's o200k_base tokenizer. Browser-side via js-tiktoken. Exact.

Pricing notes

$30 input / $180 output per 1M (short context). No cached-input rate, Pro tiers don't qualify for OpenAI's caching discount.

Long-context tier above 128K input: $60 / $270 per 1M. This calculator uses the short-context rate.

For a 1,000-token prompt + 200-token reply: $0.066 per call, $66,000 per 1M calls. That's 6× base GPT-5.5 ($11,000/M) and 32× GPT-5.4 ($2,450/M) for the same workload.

When to use GPT-5.5 Pro

When not to use it:

Common questions

GPT-5.5 Pro vs Claude Opus 4.8?

GPT-5.5 Pro: $30/$180. Claude Opus 4.8: $5/$25. Opus is dramatically cheaper, 6× cheaper on input, 7× on output. The Opus 4.8 tokenizer produces up to 35% more tokens for the same text, but even after that adjustment Opus is still 4-5× cheaper. For most premium-reasoning workloads, Opus is the rational default; reach for GPT-5.5 Pro only when you've measured it winning on your specific task.

GPT-5.5 Pro vs o3-pro?

o3-pro: $20/$80, 33% cheaper on input, 55% cheaper on output. o3-pro bills you for invisible reasoning tokens (typical 5-15× output overhead) which narrows the gap. On most reasoning benchmarks they're competitive, test both.

Does Pro have a different context window?

Same 400K as base GPT-5.5. The Pro upgrade is reasoning capacity, not context.

Compare GPT-5.5 Pro to other models