How Many Tokens?

← All models

GPT-5.5: token counter & pricing

OpenAI · exact (uses official tokenizer) · pricing as of 2026-04-27.

Provider
OpenAI
API model ID
gpt-5.5
Context window
400,000 tokens
Input price
$5.00 per 1M tokens
Output price
$30.00 per 1M tokens
Tokenizer accuracy
exact (uses official tokenizer)
Pricing as of
2026-04-27

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

What is GPT-5.5?

GPT-5.5 is OpenAI's current flagship model, released April 24, 2026. The successor to GPT-5.4 — better at coding, computer use, and multi-step research. The model that replaced GPT-4o in ChatGPT as the default for paid users.

How tokens are counted here

GPT-5.5 uses OpenAI's o200k_base tokenizer — the same one as the rest of the GPT-5 family and GPT-4o. We compute counts in your browser via js-tiktoken. Your prompt never leaves your device for OpenAI counts. Exact.

Pricing notes

GPT-5.5 has two tiers:

Cached input is heavily discounted at $0.50/M (10% of standard) — Anthropic-style prompt caching. If you're using long system prompts repeatedly, the savings are material.

Regional processing endpoints (data residency) are charged a 10% uplift.

When to use GPT-5.5

When not to use it:

Common questions

How does GPT-5.5 compare to Claude Opus 4.7?

Comparable reasoning quality on most benchmarks. Claude Opus 4.7 is $5/$25; GPT-5.5 is $5/$30 — roughly equivalent on input, Opus is 20% cheaper on output. Note Opus 4.7's new tokenizer can produce ~35% more tokens for the same text, which can flip the cost comparison on heavy-output workloads. The calculator above shows actual costs.

Should I migrate from GPT-4o to GPT-5.5?

Yes for new work. For existing production workloads with stable evals on GPT-4o, evaluate first — quality is generally better but behavior shifts. GPT-4o is still callable via the API after its February 2026 ChatGPT retirement.

What's the difference between GPT-5.5 and GPT-5.5 Pro?

Pro is positioned for the hardest reasoning tasks — same model family, much higher per-token rate ($30/$180). Use Pro only when you've measured 5.5 falling short.

Compare GPT-5.5 to other models