Gemma 4 26B A4B IT

Google · Text · Context 262.1K · max output 131.1K tokens

gemma-4-26b-a4b-it Try

Prompt caching
14% below list price

Pricing

Per 1 million tokens
	MarkasAI	Vendor list price
Input	Rp 2.294	Rp 2.684
Output	Rp 9.173	Rp 10.734
Cache	Rp 231
Cache write	Rp 2.294

MarkasAI sale prices in Rupiah, read from the same catalog as GET /v1/models. Prices can change and apply to later requests.

Specifications

Model ID: gemma-4-26b-a4b-it
Provider: Google
Type: Text
Endpoint: POST /v1/chat/completions
Context window: 262,144 tokens
Output limit per request: 131,072 tokens

About this model

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...

Quoted from the provider's public catalog, in English.

Call example

curl https://api.markas.ai.id/v1/chat/completions \
  -H "Authorization: Bearer $MARKASAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-26b-a4b-it",
    "messages": [{"role": "user", "content": "What is an API?"}],
    "max_tokens": 300
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.markas.ai.id/v1", api_key=os.environ["MARKASAI_API_KEY"])

resp = client.chat.completions.create(
    model="gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "What is an API?"}],
    max_tokens=300,
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.markas.ai.id/v1", apiKey: process.env.MARKASAI_API_KEY });

const resp = await client.chat.completions.create({
  model: "gemma-4-26b-a4b-it",
  messages: [{ role: "user", content: "What is an API?" }],
  max_tokens: 300,
});
console.log(resp.choices[0].message.content);

Keep your API key in the MARKASAI_API_KEY environment variable. Read the endpoint docs

All models