Gemma 4 26B A4B

google/gemma-4-26b-a4b-it
by Google · text+image+video in · text out · 262.1K ctx · 2026-04-03

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Desp…

Endpoints:/v1/chat/completions
INPUT$0.06/ 1M tokens
OUTPUT$0.33/ 1M tokens
p50 TTFT2.54 s7d
p95 TTFT7.49 s7d
TRAFFIC24.7Ktokens / 7d
▶ Try in playground</> Use via API
Code samples
from openai import OpenAI

client = OpenAI(
    base_url="https://orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
Pricing
Input / 1M tokens$0.060
Output / 1M tokens$0.330
Cache read / 1M$0.0075
CurrencyUSD
Performancelast 7 days
TTFT p50
2.54 s
Output speed
71.1 tok/s
TTFT p95
7.49 s
Error rate
4.3%
Public benchmarksLast evaluated 2026-04-02
AA Coding
22.4
AA Intelligence
31.2
GPQA Diamond
79.2
Humanity's Last Exam
18.3
IFBench
72.4
Long-Context Recall
55.7
SciCode
40.0
TerminalBench Hard
13.6
τ²-Bench
43.6
Source: artificialanalysis.ai
More from GoogleSee all models from google →
Gemini 3.1 Pro PreviewFlagship
google/gemini-3.1-pro-preview
$4.00 in · $18.00 out / 1M
1.05M ctx· quality 10/10
Gemini 3.1 Pro Preview Custom Tools
google/gemini-3.1-pro-preview-customtools
$4.00 in · $18.00 out / 1M
1.05M ctx· quality 10/10
Gemini 3 Flash PreviewCheapest
google/gemini-3-flash-preview
$0.50 in · $3.00 out / 1M
1.05M ctx· quality 9/10
FAQ
How much does Google: Gemma 4 26B A4B cost on OrcaRouter?
Google: Gemma 4 26B A4B is priced at $0.06 per 1M input tokens and $0.33 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is Google: Gemma 4 26B A4B's context window?
Google: Gemma 4 26B A4B supports a context window of 262K tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Google: Gemma 4 26B A4B via the OpenAI SDK?
Set OpenAI base_url to https://orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="google/gemma-4-26b-a4b-it" in the chat.completions.create call.
Does OrcaRouter rate-limit Google: Gemma 4 26B A4B?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.
Embed this badgePaste into your blog post
Google: Gemma 4 26B A4B•$0.06/M in•2543ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/google/gemma-4-26b-a4b-it" target="_blank"> <img src="https://www.orcarouter.ai/embed/google/gemma-4-26b-a4b-it.svg" alt="Google: Gemma 4 26B A4B on OrcaRouter" /> </a>
Markdown [![Google: Gemma 4 26B A4B](https://www.orcarouter.ai/embed/google/gemma-4-26b-a4b-it.svg)](https://www.orcarouter.ai/models/google/gemma-4-26b-a4b-it)