Google

Gemma 4 26B-A4B Instruct

About

Gemma 4 26B-A4B Instruct is an open-weight model from Google. Google Gemma 4 26B MoE (4B active), instruction-tuned. Text, up to 64 images, or one video per request. It accepts text, images, and video. Context window is 80K. Released May 1, 2026.

Context window
80K
Tokens of context on a request.
License
—
License on the weights.

Pricing

Token rates are US dollars per 1M tokens. Image rates are per 1K images. Audio rates are per 1M audio seconds.

Rate	Price
Input / 1M	$0.10
Cached input / 1M	$0.05
Output / 1M	$0.30

Compare

Gemma 4 26B-A4B Instruct is one of the catalog's detection models. The table is each model's published price, size, and context.

Model	What it does	Price	Parameters	Context
Gemma 4 26B-A4B Instruct	Google Gemma 4 26B MoE (4B active), instruction-tuned. Text, up to 64 images, or one video per request.	$0.10 / 1M input	—	80K
PP-OCRv6	PaddleOCR PP-OCRv6 medium text detection and recognition; scene OCR JSONL on image chat; text returns plain text; document_url fan-out via text.	$0.02 / 1M input	20M	—
DiffusionGemma 26B-A4B	Block-diffusion Gemma 4 26B-A4B: chat over text and up to 8 images, and System One typed decisions on POST /typesafe/v1/systemone.	$0.35 / 1M input	26B	16K
Gemini 3.5 Flash Lite	Fastest and cheapest Gemini tier. Multimodal chat; emits no reasoning tokens.	$0.30 / 1M input	—	1M

Benchmarks

Published scores for Gemma 4 26B-A4B Instruct, from the Gemma 4 model card.

Evals

Reading	Example
Qualitative	Clear structure, grounded in the input
Quantitative	MMMU Pro: 73.8.
Cost and performance	Lower listed rate, mid-pack latency

Performance

Latency is the end-to-end round trip. Throughput is completion tokens divided by that time. It is a request rate, not decode speed.

Latency
154 ms
Throughput
6,797 tok/s
Requests
89

Methods

Methods this model serves.

Method	Returns
detection	Boxes around objects
chat	The model's reply

Estimate cost

Estimate. An hour of video is 15 frames a minute at 144 tokens a frame, plus the audio in that request, and 500 output tokens a minute.

Hours of video

$33.48

Quick start

Call this model on the OpenAI-compatible gateway. The model id is already filled in.

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "What is in this image?"}],
)

print(response.choices[0].message.content)