Google: Gemma 4 26B A4B

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

HealthyOpen weights

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...

Context

262Ktokens

About 374 pages of text at once

Max output

236Ktokens

About 337 pages in one answer

Intelligence

—

No score published for this model.

Output speed

63tokens/s

A 500-word answer in about 11.1 s

From public market statistics for this model

First token

0.6s

Reasoning models start later

From public market statistics for this model

Health, 30 days

95.32%

23 of 30 days without a fault

IranRouter’s measurements

Price & cost

Every rate in Rial. A request pays only for the tokens it actually uses.

Input	184,678	IRR / 1M tokens
Output	615,592	IRR / 1M tokens
Reasoning tokensThe output rate	615,592	IRR / 1M tokens
Cache read	102,599	IRR / 1M tokens
Image input tokensThe input rate	184,678	IRR / 1M tokens

With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.

What would this model cost you a month?

Requests a day: 2,000

Input tokens per request: 1,500

Output tokens per request: 300

Share of input read from cache: 0%

Monthly cost

27.7MIRR

923K IRR a day, 462 IRR each request

30 days at today’s rate.

Rial price over 90 days

It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.

InputOutput

Performance, 30 days

Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.

Daily health95.32%

Time to first token0.70 s

Output speed52 tokens/s

Place in the market

By usage across the global model market.

Daily rank

Share of the day’s tokens

Capabilities

Image inputYes

Audio inputNo

Tool callingYes

JSON outputYes

ReasoningYes

Web searchNo

Prompt cacheYes

Makes imagesNo

Open weightsYes

On the free planNo

Input: ImageTextVideo
Output: Text

Parameters it accepts

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Other benchmarks

Coding index39

Agentic index3

Standard tests

GPQA DiamondScore: 70%Tasks: 1,584
τ-bench Verified AirlineScore: 69%Tasks: 400

Start in a minute

The official OpenAI and Anthropic SDKs; only the address and the key change.

Base URLhttps://iranrouter.com/v1

Model IDgoogle/gemma-4-26b-a4b-it

API keyCreate one in the dashboard

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://iranrouter.com/v1",
    api_key="ir-...",
)

r = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Hello, introduce yourself"}],
)
print(r.choices[0].message.content)

The full guide in the docs: keys, streaming and errors

Peer models

Its family and models with a close score; the last column compares one message’s cost with this model.

No peer models found.

Technical specs

ID: google/gemma-4-26b-a4b-it
Maker: Google
Tokenizer: Gemma
Released: Apr 3, 2026
Added to IranRouter: Aug 25, 2026
Context: 262,144 tokens
Max output: 235,929 tokens
Weights: google/gemma-4-26B-A4B-it

Default parameters

top_k=64top_p=0.95temperature=1

Scores by Artificial Analysis, as of Oct 31, 2026

Google: Gemma 4 26B A4BOne message about 680 IRRStart with this model