Google DeepMind

Gemma 4 26B A4B IT

Generally availableOpen weights262K contextReasoning

Summary

Gemma 4 26B A4B IT is an open-weight language model from Google DeepMind, released on 2 Apr 2026. It accepts text and images and generates text, with a 262K-token context window and up to 33K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $0.30 per million output tokens (OpenRouter), across 10 providers we track.

Open Gemma instruction model for efficient chat and self-hosted deployments

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperGoogle DeepMind
Release date2 Apr 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters25.8B [Hugging Face]
Context window262K (262,144 tokens) [models.dev]
Max output33K tokens [models.dev]
Knowledge cutoffApr 2025 [models.dev]
InputText and images [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Facegoogle/gemma-4-26B-A4B-it [Hugging Face]

Gemma 4 26B A4B IT API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Gemini API
gemma-4-26b-a4b-it
FreeFree–262Kmodels.dev, 18 Nov 2026
DeepInfra
google/gemma-4-26B-A4B-it
$0.07$0.34–262Kmodels.dev, 18 Nov 2026
OpenRouter
google/gemma-4-26b-a4b-it
$0.09$0.30$0.05262KOpenRouter, 18 Nov 2026
Cloudflare Workers AI
@cf/google/gemma-4-26b-a4b-it
$0.10$0.30$0.05256Kmodels.dev, 18 Nov 2026
Amazon Bedrock
google.gemma-4-26b-a4b
$0.13$0.40–262Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
google/gemma-4-26B-A4B-it
$0.13$0.40–262Kmodels.dev, 18 Nov 2026
Novita AI
google/gemma-4-26b-a4b-it
$0.13$0.40–262Kmodels.dev, 18 Nov 2026
SiliconFlow
google/gemma-4-26B-A4B-it
$0.14$0.40$0.05262Kmodels.dev, 18 Nov 2026
Google Vertex AI
google/gemma-4-26b-a4b-it-maas
$0.15$0.60$0.01262Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
google/gemma-4-26b-a4b-it
$0.15$0.60$0.01262Kmodels.dev, 18 Nov 2026

Running Gemma 4 26B A4B IT locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)16 GB17 GB18 GB
Q8_0 (8-bit)27 GB29 GB30 GB
FP16 / BF16 (16-bit)52 GB53 GB54 GB

At 4-bit with an 8K conversation, Gemma 4 26B A4B IT needs about 17 GB, so it fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.

Frequently asked questions

What is the context window of Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT has a context window of 262,144 tokens (262K) and can generate up to 32,768 tokens in a single response, according to models.dev.

How much does the Gemma 4 26B A4B IT API cost?

Through Gemini API, Gemma 4 26B A4B IT costs Free per million input tokens and Free per million output tokens. Prices last verified 18 Nov 2026.

Is Gemma 4 26B A4B IT open source?

Gemma 4 26B A4B IT is an open-weight model: its weights are published on Hugging Face as google/gemma-4-26B-A4B-it under the apache-2.0 license. Check the license terms before commercial use.

When was Gemma 4 26B A4B IT released?

Google DeepMind released Gemma 4 26B A4B IT on 2 Apr 2026, according to models.dev.

Which providers offer Gemma 4 26B A4B IT?

We track Gemma 4 26B A4B IT on 10 providers: Gemini API, DeepInfra, OpenRouter, Cloudflare Workers AI, Amazon Bedrock, Hugging Face Inference Providers, Novita AI, SiliconFlow, Google Vertex AI, Vercel AI Gateway.

How much VRAM does Gemma 4 26B A4B IT need?

About 17 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 29 GB at 8-bit. The 4-bit model fits on a graphics card with 24 GB or more, such as the NVIDIA GeForce RTX 3090 24 GB. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
NVIDIA Nemotron 3 Super 120B A12BNVIDIA11 Mar 2026262K$0.07$0.40Open
Step 3.5 FlashStepFun29 Jan 2026262K$0.10$0.30Open
Qwen/Qwen3.5-9BAlibaba (Qwen)23 Feb 2026262K$0.10$0.15Open
Mistral Small 4Mistral AI16 Mar 2026262K$0.15$0.60Open
Ministral 14BMistral AI2 Dec 2025262K$0.20$0.20Open
Hy3 previewTencent (Hunyuan)20 Apr 2026262K$0.18$0.60Open

Change history

  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • OpenRouter price changed: input $0.08 → $0.09, output $0.10 → $0.30 per 1M tokens
  • Gemini API price changed: input – → Free, output – → Free per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.08, output $0.30 → $0.10 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • OpenRouter price changed: input $0.02 → $0.09, output $0.05 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.08 → $0.02, output $0.24 → $0.05 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.08, output $0.26 → $0.24 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.09, output $0.20 → $0.26 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.07, output $0.23 → $0.20 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • SiliconFlow price changed: input $0.12 → $0.14, output $0.40 → $0.40 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens
  • OpenRouter price changed: input $0.09 → $0.07, output $0.30 → $0.23 per 1M tokens
  • Now listed on Google Vertex AI
  • OpenRouter price changed: input $0.07 → $0.09, output $0.23 → $0.30 per 1M tokens

Sources