tokenstat
tokenstat

Google: Gemma 3 4B IT

google/gemma-3-4b-it · rates as of · Benchmarks · Plans · Calculator

Open Gemma instruction model for efficient chat and self-hosted deployments

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
131K
tokens
Offers
9
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.devcheapestgoogle/gemma-3-4b-itNVIDIA$0$0$0131K
models.devgoogle.gemma-3-4b-itAmazon Bedrock$0.04$0.08$0128K
LiteLLMgoogle/gemma-3-4b-it$0.04$0.08$0.004
LiteLLMgoogle.gemma-3-4b-it$0.04$0.08$0.004
LiteLLMdeepinfra/google/gemma-3-4b-it$0.04$0.08$0.004
LiteLLMgemma-3-4b-it$0.04$0.08$0.004
models.devgoogle/gemma-3-4b-itKilo Gateway$0.05$0.1$0131K
OpenRoutergoogle/gemma-3-4b-itOpenRouter$0.05$0.1$0131K
models.devunsloth/gemma-3-4b-itNanoGPT$0.2006$0.2006$0128K

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: pdf
  • Out: text
Knowledge cutoff: 2024-08-31Released: 2025-03-13Family: gemma

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

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