GPT-5 Pro: token counter & pricing
OpenAI · exact (uses official tokenizer) · pricing as of 2026-05-31.
- Provider
- OpenAI
- API model ID
gpt-5-pro- Context window
- 400,000 tokens
- Input price
- $15.00 per 1M tokens
- Output price
- $120.00 per 1M tokens
- Tokenizer accuracy
- exact (uses official tokenizer)
- Pricing as of
- 2026-05-31
Open the counter to count tokens for GPT-5 Pro in real time.
What is GPT-5 Pro?
GPT-5 Pro is the premium tier of OpenAI's original GPT-5, same o200k_base tokenizer and 400K context as the rest of the GPT-5 family, scaled-up reasoning capacity at a premium per-token rate. $15 input / $120 output per 1M tokens.
It sits between base GPT-5 ($1.25/$10) and the more recent GPT-5.5 Pro ($30/$180). For workloads tuned on the original GPT-5 that need a quality bump without jumping a full generation, GPT-5 Pro is the in-family upgrade.
How tokens are counted here
OpenAI's o200k_base tokenizer. Browser-side via js-tiktoken. Exact.
Pricing notes
$15 input / $120 output per 1M. No cached-input rate, Pro tiers don't qualify for caching.
For 1,000 input + 200 output: $0.039 per call, $39,000 per 1M calls. That's 12× base GPT-5 ($3,250/M) for the same workload, same multiplier as 5.2 Pro and 5.4 Pro relative to their base tiers.
When to use GPT-5 Pro
- Workloads pinned to GPT-5's specific behavior profile that need a reasoning lift without switching generations.
- Stable production agents where switching to GPT-5.5 Pro requires re-validation you don't want to do.
- Eval-ceiling testing for the original GPT-5 family.
When not to use it:
- New work. GPT-5.5 Pro is the current flagship Pro.
- Most cost-sensitive workloads, base GPT-5 covers them at 1/12 the price.
- Tasks that benefit from explicit reasoning, o3 / o3-pro are designed for that.
Common questions
Should I migrate from GPT-5 Pro to GPT-5.5 Pro?
GPT-5.5 Pro is $30/$180, exactly 2× the GPT-5 Pro rate. Migration pays off if your evals show the upgrade winning. For stable workloads with no measured win, the 2× spend isn't justified.
Cached-prompt savings?
Not available on Pro tier. If caching savings matter to your cost model, use base GPT-5 ($1.25/$10 with $0.125/M cached), the savings on a heavily-cached workload often outweigh the quality difference.
How does GPT-5 Pro compare to o1?
o1: $15/$60. Same input rate, half the output rate. o1 bills for invisible reasoning tokens which can reverse the apparent advantage. Both are legacy reasoning models at this price tier, for new work use o3 ($2/$8) or o3-pro ($20/$80).
Compare GPT-5 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-5.2 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-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)