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
- Highest-stakes reasoning tasks, legal drafts, regulatory analysis, complex code architecture.
- Workloads where you've measured GPT-5.5 falling short on a specific eval.
- Eval ceiling testing for the GPT-5.5 family, what's the best the family can do.
When not to use it:
- Anywhere base GPT-5.5 hits your accuracy bar.
- High-volume workloads, 6× costs at scale.
- Tasks better suited to o3-pro ($20/$80) which is positioned for explicit reasoning at lower price.
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
- GPT-5.5 (OpenAI, $5.00/$30.00)
- 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-5.2 Pro (OpenAI, $21.00/$168.00)
- 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)