tokenstat
tokenstat

OpenAI: GPT-5.2 Pro

openai/gpt-5.2-pro · rates as of · Benchmarks · Plans · Calculator

Frontier GPT model for professional reasoning, coding, and multimodal work

Cheapest input
$18.90
$/MTok · models.dev
Cheapest output
$151.20
$/MTok
Context
400K
tokens
Offers
13
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.devcheapestgpt-5.2-proJiekou.AI$18.90$151.20$0400K
models.devopenai/gpt-5.2-proPoe$19$150$0400K
models.devopenai/gpt-5.2-proKilo Gateway$21$168$0400K
models.devopenai/gpt-5.2-proNanoGPT$21$168$0400K
models.devgpt-5.2-proOpenAI$21$168$2.10400K
OpenRouteropenai/gpt-5.2-proOpenRouter$21$168$2.10400K
models.devopenai/gpt-5.2-proOrcaRouter$21$168$0400K
models.devopenai/gpt-5.2-proRequesty$21$168$0400K
models.devopenai/gpt-5.2-proVercel AI Gateway$21$168$0400K
models.devopenai/gpt-5.2-proZenMux$21$168$0400K
models.devgpt-5.2-proLLM Gateway$21$168$0400K
LiteLLMgpt-5.2-pro$21$168$2.10
LiteLLMazure/gpt-5.2-pro$21$168$2.10

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: image
  • In: text
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-08-31Released: 2026-01Family: 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