Atlas / Models / Google / Google: Gemma 4 26B A4B

Google: Gemma 4 26B A4B✓ Catalog verified

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

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Input price
$0.07 /1M
Output price
$0.34 /1M
Context
262K
Modalities
imagetextvideo
Released
Apr 3, 2026
Tool calling
✓ Yes
Atlas signal
86/100
01

Overview

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Access: available through the official Google API. Context window: 262K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 6, 2026
02

Specifications

API identifiergoogle/gemma-4-26b-a4b-it
ProviderGoogle
Model typeMultimodal LLM
Context window262K catalog
Input modalitiesimage · text · video
Output modalitiestext
ReleasedApr 3, 2026
TokenizerGemma
ModeratedNo
Architecture modalitytext+image+video->text
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Source: provider documentation + catalog feedMethodology →

API defaults

Default parameters
{
  "top_k": 64,
  "top_p": 0.95,
  "temperature": 1
}
03

Pricing

Live pricing components for google/gemma-4-26b-a4b-it as published in the catalog.

$0.07
Input /1M
$0.34
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$7e-8$0.07 / 1MPer input token
Completion tokens$3.4e-7$0.34 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.1Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Google: Gemma 4 26B A4B
MMLU Signal (Reasoning)
91signal
Coding Signal (HumanEval proxy)
88signal
Math Signal (GSM8K proxy)
83signal
Science Signal (GPQA proxy)
83signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Google: Gemma 4 26B A4B through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Google: Gemma 4 26B A4B cost?

$0.07 per 1M input tokens and $0.34 per 1M output tokens on the official Google API.

What is the context window of Google: Gemma 4 26B A4B?

Google: Gemma 4 26B A4B supports up to 262K tokens of context.

Does Google: Gemma 4 26B A4B support tool / function calling?

Yes, Google: Gemma 4 26B A4B supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Google: Gemma 4 26B A4B?

Use the official Google API with the model id `google/gemma-4-26b-a4b-it`. See the Quick start section above for code examples.