tokenstat
tokenstat

OpenAI: GPT-5.5 Pro

openai/gpt-5.5-pro · rates as of · Benchmarks · Plans · Calculator

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

Cheapest input
$27.27
$/MTok · models.dev
Cheapest output
$163.64
$/MTok
Context
1.1M
tokens
Offers
14
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestopenai/gpt-5.5-proPoe$27.27$163.64$0400K
models.devopenai/gpt-5.5-proCrossModel$30$180$01.1M
models.devopenai/gpt-5.5-proFastRouter$30$180$01.1M
models.devopenai/gpt-5.5-proImpossibl$30$180$31.1M
models.devopenai/gpt-5.5-proKilo Gateway$30$180$01.1M
models.devgpt-5.5-proOpenAI$30$180$01.1M
OpenRouteropenai/gpt-5.5-proOpenRouter$30$180$01.1M
models.devopenai/gpt-5.5-proOrcaRouter$30$180$01.1M
models.devopenai/gpt-5.5-proVercel AI Gateway$30$180$01M
models.devopenai/gpt-5.5-proZenMux$30$180$01.1M
models.devgpt-5.5-proLLM Gateway$30$180$01.1M
models.devgpt-5.5-proOpenCode Zen$30$180$301.1M
LiteLLMgpt-5.5-pro$30$180$3
LiteLLMazure/gpt-5.5-pro$30$180$3

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • In: file
  • Out: text
  • Out: image
Knowledge cutoff: 2025-12-01Released: 2026-04-23Family: gpt-pro

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash