Gemma 4 26B A4B
Gemma 4 26B A4B (Google, 2026) is an image-generation 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...
by Google · 262K token context window
Best for
- image generation from text
- creative design and ideation
Ways to use Gemma 4 26B A4B in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Google API key. osFoundry discovers Gemma 4 26B A4B automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Run Gemma 4 26B A4B yourself
Gemma 4 26B A4B is also available as open weights — self-host it for full data control and no per-token cost. See that page for GPU requirements and a cost comparison against API pricing.
Gemma 4 26B A4B vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| Gemma 4 26B A4B | Google | — | 262K | $ 0.060 /1M | API only |
| Claude Opus 4.6 (Fast) | Anthropic | — | 1000K | $ 30.00 /1M | API only |
| Qwen3.6 Plus | Qwen | — | 1000K | $ 0.325 /1M | API only |
| Kimi K2.6 | MoonshotAI | — | 262K | $ 0.740 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Gemma 4 26B A4B
How much does Gemma 4 26B A4B cost?
Gemma 4 26B A4B is metered at $ 0.060 /1M for input, and $ 0.330 /1M for output. Bring your own Google API key — osFoundry passes through provider pricing without markup.
Can I use Gemma 4 26B A4B commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Gemma 4 26B A4B ?
Gemma 4 26B A4B supports a 262K token context window.
Can I run Gemma 4 26B A4B locally?
No — Gemma 4 26B A4B is hosted only and accessed via the Google API. An open-weights equivalent is available to self-host — see the cross-link above.
What is Gemma 4 26B A4B best at?
Gemma 4 26B A4B is well-suited to image generation from text, creative design and ideation.
How do I use Gemma 4 26B A4B in osFoundry?
Paste your Google API key in the key dialog (or deploy the open weights for self-hostable models), assign Gemma 4 26B A4B to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Google on April 3, 2026. Source: https://openrouter.ai/google/gemma-4-26b-a4b-it