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:
- Short context (≤128K input): $5 input / $30 output per 1M tokens
- Long context (>128K input): $10 input / $45 output per 1M tokens (the calculator above shows the short-context rate)
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
- Frontier reasoning that GPT-5.4 measurably falls short on.
- Multi-step coding agents — improved tool use vs prior generation.
- Long-context analysis where 400K input is needed.
- Default replacement for GPT-4o workloads that have shifted off the deprecated model.
When not to use it:
- Cost-sensitive workloads — GPT-5.4 is half the input price, GPT-5.4 Mini is a sixth.
- High-volume classification or extraction — GPT-5 Nano at $0.05 input is dramatically cheaper.
- Tasks where Claude's instruction-following nuance still wins.
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
- 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-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 4.7 (Anthropic, $5.00/$25.00)
- Llama 3.1 405B (Meta, $3.50/$3.50)
- Claude Sonnet 4.6 (Anthropic, $3.00/$15.00)