Gemma / gemma/gemma-4-26b-a4b-it

Gemma 4 26B A4B - access through LLMTR

Gemma 4 26B A4B is Google's open-weight Mixture-of-Experts model from the Gemma 4 family: a sparse architecture that activates 3.8 billion of its 25.2 billion parameters per token, giving it inference speed close to a 4B model with much larger model capacity behind it. It offers a 262,144-token context window, native tool calling, JSON object mode and JSON Schema structured output. Step-by-step reasoning is available but off by default; turning it on returns the reasoning trace separately from the answer, and reasoning tokens are billed as output. It accepts text and image input at variable aspect ratios and resolutions, and produces text only; audio and video input are not supported at this size. There is no separate output ceiling below the context window, and no prompt-cache discount is applied — every request bills at the full input rate.

Technical specifications

Canonical IDgemma/gemma-4-26b-a4b-it
ProviderGemma
Context window262,144 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.070000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.340000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemma/gemma-4-26b-a4b-it","messages":[{"role":"user","content":"Hello"}]}'

Related models