tokenstat
tokenstat

Google: Gemini 3 Flash Preview

google/gemini-3-flash · rates as of · Benchmarks · Plans · Calculator

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Cheapest input
$0.4
$/MTok · models.dev
Cheapest output
$2.40
$/MTok
Context
1.0M
tokens
Offers
5
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.devcheapestgoogle/gemini-3-flashPoe$0.4$2.40$0.041.0M
models.devgoogle/gemini-3-flashVercel AI Gateway$0.5$3$0.051M
models.devgemini-3-flashNeon$0.5$3$0.051.0M
models.devgemini-3-flashOpenCode Zen$0.5$3$0.051.0M
models.devgemini-3-flashPioneer$0.5$3$0.051.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • In: audio
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-03Released: 2025-12-17Family: gemini-flash

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