IranRouter
All models
Google

Google: Gemma 4 26B A4B

Unavailable

by Google

google/gemma-4-26b-a4b-itUsage rank #46

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...

At a glance

Context window
262Ktokens
Max output
236Ktokens
Knowledge to
Released
2026

Capabilities

CapabilitiesReasoningVisionToolsStructured output
InputImageTextVideo
OutputText
ReasoningSupported

Benchmarks

Coding index
39

Standard evaluations

BenchmarkScoreTasks
gpqa_diamond0.743,552
tau_bench_verified_airline0.681,044

Source: Artificial Analysis · as of Sep 16, 2026

Performance

Reference uptime

100%

Aug 18Sep 16

Median latency

1,048 ms

Aug 18Sep 16

Throughput

26.1 tok/s

Aug 18Sep 16

IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.

Popularity

Current rank
#46
Rank change, 7 days
0

Daily tokens · 90 days

47.4B

Jun 18Sep 15

Ranked by daily token volume across the global model market; the figure above the chart is the daily average.

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Parameters this model accepts; anything else is ignored.

Quick start

from openai import OpenAI

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

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

Only base_url and the key change; the rest of your code stays as it is.