tokenstat
tokenstat

Google: Gemma 4 26B A4B IT

google/gemma-4-26B-A4B-it · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.06
$/MTok · models.dev
Cheapest output
$0.33
$/MTok
Context
262K
tokens
Offers
19
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.devcheapestgoogle/gemma-4-26b-a4b-itOrcaRouter$0.06$0.33$0262K
models.devgoogle/gemma-4-26B-A4B-itDeepInfra$0.07$0.34$0262K
models.devgoogle/gemma-4-26b-a4b-itKilo Gateway$0.07$0.34$0262K
OpenRoutergoogle/gemma-4-26b-a4b-itOpenRouter$0.07$0.34$0262K
models.devgemma-4-26b-a4b-itLLM Gateway$0.07$0.34$0262K
models.dev@cf/google/gemma-4-26b-a4b-itCloudflare$0.1$0.3$0256K
LiteLLM@cf/google/gemma-4-26b-a4b-it$0.1$0.3$0.01
LiteLLMgemma-4-26b-a4b-it$0.1$0.3$0.01
LiteLLMcloudflare/@cf/google/gemma-4-26b-a4b-it$0.1$0.3$0.01
models.devgoogle/gemma-4-26B-A4B-itSiliconFlow$0.12$0.4$0262K
models.devgoogle/gemma-4-26B-A4B-itHugging Face$0.13$0.4$0262K
models.devgoogle/gemma-4-26b-a4b-itMerge Gateway$0.13$0.4$0262K
models.devgoogle/gemma-4-26b-a4b-itNanoGPT$0.13$0.4$0262K
models.devgoogle/gemma-4-26b-a4b-itNovita AI$0.13$0.4$0262K
models.devgemma-4-26b-a4b-itCharm Hyper$0.13$0.43$0256K
models.devgoogle/gemma-4-26B-A4B-itEvroc$0.144$0.575$0262K
models.devgoogle/gemma-4-26b-a4b-itVercel AI Gateway$0.15$0.6$0.015262K
models.devgemma-4-26b-a4b-itScaleway$0.25$0.5$0.025256K
LiteLLMgoogle/gemma-4-26b-a4b-it$0.25$0.5$0.025

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-04Released: 2026-04-30Family: 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