tokenstat
tokenstat

GPT Image 2

azure/gpt-image-2 · rates as of · Benchmarks · Plans · Calculator

Image model for prompt-driven generation, editing, and visual design workflows

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
400K
tokens
Offers
8
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. Showing free/$0 offers. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestgpt-image-2Kenari$0$0$0272K
models.devgpt-image-2Azure$5$30$1.25
models.devgpt-image-2OpenAI$5$30$1.25
models.devopenai/gpt-image-2Vercel AI Gateway$5$30$1.25
LiteLLMazure/gpt-image-2$5$10$1.25
LiteLLMgpt-image-2$5$10$1.25
models.devopenai/gpt-image-2Poe$5.05$32.32$1.26
OpenRouteropenai/gpt-image-2OpenRouter$8$8$2400K

Capabilities

  • Attachments
  • In: text
  • In: image
  • Out: image
Released: 2026-04-21Family: gpt-image

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