All AI models · LLM benchmarks · Methodology

Google

Gemma 4 26B A4B

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

Model facts

Context window
262K tokens
Maximum output
33K tokens
Cheapest paid input
$0.042 per 1M tokens
Cheapest paid output
$0.22 per 1M tokens
Open weights
yes
Providers
24

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video, pdf.

Local hardware estimate

At 4K context: Q4_K_M 15.0 GiB, Q8_0 27.0 GiB, F16 49.6 GiB working memory.

Parameters
25.8 billion
Architecture
gemma4
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning26.139.3not measurednot measured
Non-reasoning20.4not measurednot measured68.8

Observed price history

  • 2026-08-24: $0.042 input / $0.22 output per 1M tokens

API providers

  • NaN — model id gemma4; free input / free output per 1M tokens; provider documentation
  • OpenRouter (free) — model id google/gemma-4-26b-a4b-it:free; free input / free output per 1M tokens; provider documentation
  • Kilo Gateway — model id google/gemma-4-26b-a4b-it; $0.042 input / $0.22 output per 1M tokens; provider documentation
  • EmpirioLabs AI — model id gemma-4-26b-a4b; $0.05 input / $0.29 output per 1M tokens; provider documentation
  • OrcaRouter — model id google/gemma-4-26b-a4b-it; $0.06 input / $0.33 output per 1M tokens; provider documentation
  • Cloudflare Workers AI — model id @cf/google/gemma-4-26b-a4b-it; $0.1 input / $0.3 output per 1M tokens; provider documentation
  • OpenRouter — model id google/gemma-4-26b-a4b-it; $0.07 input / $0.34 output per 1M tokens; provider documentation
  • Deep Infra — model id google/gemma-4-26B-A4B-it; $0.07 input / $0.34 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id gemma-4-26b-a4b-it; $0.07 input / $0.34 output per 1M tokens; provider documentation
  • Requesty — model id gemma-4-26b-a4b-it; $0.07 input / $0.34 output per 1M tokens; provider documentation
  • Charm Hyper — model id gemma-4-26b-a4b-it; $0.106 input / $0.368 output per 1M tokens; provider documentation
  • NanoGPT — model id google/gemma-4-26b-a4b-it; $0.12 input / $0.38 output per 1M tokens; provider documentation
  • SiliconFlow — model id google/gemma-4-26B-A4B-it; $0.12 input / $0.4 output per 1M tokens; provider documentation
  • Hugging Face — model id google/gemma-4-26B-A4B-it; $0.13 input / $0.4 output per 1M tokens; provider documentation
  • Merge Gateway — model id google/gemma-4-26b-a4b-it; $0.13 input / $0.4 output per 1M tokens; provider documentation
  • NovitaAI — model id google/gemma-4-26b-a4b-it; $0.13 input / $0.4 output per 1M tokens; provider documentation
  • Venice AI — model id google-gemma-4-26b-a4b-it; $0.13 input / $0.4 output per 1M tokens; provider documentation
  • AKI.IO — model id gemma4-26b; $0.1 input / $0.5 output per 1M tokens; provider documentation
  • Cortecs — model id gemma-4-26b-a4b-it; $0.111 input / $0.557 output per 1M tokens; provider documentation
  • evroc — model id google/gemma-4-26B-A4B-it; $0.144 input / $0.575 output per 1M tokens; provider documentation
  • Scaleway — model id gemma-4-26b-a4b-it; $0.25 input / $0.5 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id google/gemma-4-26b-a4b-it; $0.15 input / $0.6 output per 1M tokens; provider documentation
  • Arena — model id significant-otter; not published input / not published output per 1M tokens; provider documentation
  • Google — model id gemma-4-26b-a4b-it; not published input / not published output per 1M tokens; provider documentation