Post-Cutoff
Search For AI agents

Google DeepMindGemma familyCurrentLanguage modelReleased 2 Apr 2026

Gemma 4

Latest open-weights family from Google DeepMind (built from Gemini 3 research); run locally or self-host.

Model idgoogle/gemma-4-31B-it

Price$0.09 in, $0.34 out per 1M tokens

Checked29 September 2026

No published training cutoff

At least1,887events since its release on 2 April 2026

85 historic, 432 major. 225 days of news.

Google DeepMind doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

8 ways to use Gemma 4, with the model id each provider expects.

Providers, model ids, endpoints and docs for Gemma 4
ProviderModel idEndpointDocs
Hugging Face google/gemma-4-31B-it huggingface.co
Hugging Face google/gemma-4-26B-A4B-it huggingface.co
Hugging Face google/gemma-4-12B-it huggingface.co
Hugging Face google/gemma-4-E4B-it huggingface.co
Hugging Face google/gemma-4-E2B-it huggingface.co
OpenRouter google/gemma-4-31b-it
OpenRouter google/gemma-4-26b-a4b-it
Google docs ai.google.dev

Pricing

Prices for Gemma 4
Input$0.09 per 1M tokens
Output$0.34 per 1M tokens

As published: “per 1M tokens, OpenRouter price for google/gemma-4-31b-it (26B-A4B: $0.09 / $0.30; free variants exist). Weights free to download”.

Source: openrouter.ai, checked 29 September 2026.

Specs

Input
Text, images, audio and video
Output
Text
Context window
262,144 tokens
Max output
Not published
Open weights
Yes
Licence
Apache-2.0
Training cutoff
Not published
Released
2 April 2026
Status
Current
Type
Language model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • First Apache-2.0 Gemma

    First Gemma generation under the permissive Apache 2.0 license instead of Google’s custom Gemma terms.

    Source: blog.google

  • Intelligence per parameter

    31B dense ranked #3 and 26B A4B MoE #6 among open models on Arena at launch.

    Source: blog.google

  • On-device agentic models

    E2B/E4B edge models with native audio+vision, function calling and structured JSON, running offline on phones/Raspberry Pi/Jetson.

    Source: blog.google

  • Encoder-free unified 12B

    Found after launch

    Gemma 4 12B, added later, is a unified encoder-free multimodal model with native audio.

    Source: ai.google.dev

Notes

Sizes E2B, E4B (128K context), 12B, 26B A4B MoE, 31B dense (256K context); base and -it variants plus QAT/GGUF quantized repos. 12B released later (HF repo 2026-05-23). Audio input on E2B/E4B/12B only. 140+ languages. pricing is third-party (OpenRouter), not Google.

from transformers import pipeline
pipe = pipeline("image-text-to-text", model="google/gemma-4-E4B-it")
print(pipe(text=[{"role":"user","content":[{"type":"text","text":"Hello!"}]}]))

Sources: Gemma docs, launch blog, HF repo.