Door background frame
Gemma 4 26B A4B IT
Limited Trial
Gemma 4-26B-A4B IT visualization

Gemma 4 26B A4B IT

Limited Trial
Multimodal MoE with 26B total/4B active params; handles text, image, and video input with switchable thinking, and 256K native context.

Google API Usage

POST /v1/chat/completions
import requests
import json

url = "https://api.akashml.com/v1/chat/completions"

payload = {
    "model": "google/gemma-4-26b-a4b-it",
    "messages": [
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ],
    "max_tokens": 150,
    "temperature": 0.7
}

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Pricing

Price (per 1M Tokens)
Model
Input
Output
Cache Read
Gemma 4 26B A4B IT
$0.042
$0.22

Model Details

Model Details
Provider
Google
Type
Multimodal
Parameters
26B (4B active)
Context Length
256K
Don't see the model you need?
Let us know, and we'll add it for you.
Request Model
AkashML
X (Twitter)GitHubDiscordYouTube
AI Inference Service
Akash Network
Built on Akash Network
Copyright 2026 © akashml.com