tokenstat
homepricingstatshelpsign in
tokenstat
Venice

GPT-5.2 Codex

venice/openai-gpt-52-codex · rates as of · Benchmarks · Plans · Calculator

Code-specialist GPT for repository edits, reviews, and long-running software agents

Cheapest input
$2.19
$/MTok · models.dev
Cheapest output
$17.50
$/MTok
Context
256K
tokens
Offers
1
1 source

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-52-codexVenice AI$2.19$17.50$0.219256K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2025-08Released: 2025-01-15Family: gpt

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