MODEL PROFILE

Gemma 4 26B A4B (free)

Google · gemma-4-26b-a4b-it:free

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...

Text generationreasoningtools
Context window262,144 Token
Input → OutputImage、Text、Video → Text
Model weightsOpen weights
Profile updated2026/11/8 16:36:47
OVERVIEW

Model overview

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...

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Instruction-tuned Mixture-of-Experts (MoE) architecture with 25.2B total parameters but only 3.8B activated per token
  • Supports multimodal inputs: text, image, and video
  • Optimized for reasoning and tool-use capabilities

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · google/gemma-4-26b-a4b-it ↗USD 0.0675USD 0.225Per million tokens2026/11/2 06:25:23
OpenRouter · google/gemma-4-26b-a4b-it:free ↗USD 0USD 0Per million tokens2026/11/2 06:25:23

Some channels offer cache discounts. Check the source for cache read, write and additional fees.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Is Gemma 4 26B A4B IT free to use?

Yes, it is explicitly labeled as 'free' on OpenRouter and available under the Apache-2.0 license.

What is the context length of this model?

The context length is 262,144 tokens.

Does it support multimodal input?

Yes, the inputs include 'image', 'text', and 'video'.

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。