Compare Google Gemma 4 26B A4B Instruct (MoE) with other AI models

See how Gemma 4 26B A4B Instruct (MoE) from Google compares with other AI models on price, context length and features.

Chat with Gemma 4 26B A4B Instruct (MoE)

1 model

Gemma 4 26B A4B Instruct (MoE)Google

Gemma 4's Mixture-of-Experts model. 25.2B total parameters but only 3.8B active per token, so it runs almost as fast as a 4B model while scoring close to the dense 31B.

Overview

Overview for Gemma 4 26B A4B Instruct (MoE)
Metric	Gemma 4 26B A4B Instruct (MoE)
Author	Google
Type	Text
Context length	262K tokens
Reasoning	Yes
Input modalities	TextImageVideo
Output modalities	Text
Released	Apr 2, 2026
Knowledge cutoff	January 2025
Served by	Google via Oxyy
API	Gemini · OpenAI-compatible/v1/chat/completions

Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

Pricing

Pricing for Gemma 4 26B A4B Instruct (MoE)
Metric	Gemma 4 26B A4B Instruct (MoE)
Input	$0.052 /1M inputStandard $0.130
Output	$0.160 /1M outputStandard $0.400
Cached input	$0 /1M cached
Cache write (5 min)	$0 /1M cache write
Cache write (1 hour)	$0 /1M cache write 1h
Cached audio input	$0 /1M cached audio
Reasoning	$0 /1M reasoning
Cache storage	$0 /1M token-hours
Blended price (3:1 input:output)	$0.079 /1M tokens

Includes the Launch Promo discount (60% off the standard price).

Performance

Performance for Gemma 4 26B A4B Instruct (MoE)
Metric	Gemma 4 26B A4B Instruct (MoE)
Latency (p50, 7 days)	3.54 s
Time to first token (p50)	0.93 s
Throughput (p50)	50.8 tok/s
Tokens (7 days)	87.5M

Visualize performance

Latency, daily median

Throughput, daily median

Gemma 4 26B A4B Instruct (MoE)

Features

Features for Gemma 4 26B A4B Instruct (MoE)
Metric	Gemma 4 26B A4B Instruct (MoE)
Tool use	Yes
Structured outputs	Yes
Prompt caching	Yes
Streaming	Yes
Image input	Yes

Activity

Activity for Gemma 4 26B A4B Instruct (MoE)
Metric	Gemma 4 26B A4B Instruct (MoE)
Tokens (30 days)	228.3M tokens · last 30 days
Input tokens	193.4M
Output tokens (excluding reasoning)	25.5M
Reasoning tokens	9.3M

Gemma 4 26B A4B Instruct (MoE)228.3M tokens · last 30 days

Input 193.4M
Output (excl. reasoning) 25.5M
Reasoning 9.3M

Suggested models to compare

How this comparison is built

Prices are what Oxyy charges today; where a discount applies, the standard price is shown beside it. Context window, output limit, modalities and features come from the Oxyy model catalog. Latency, time to first token and throughput are medians measured on Oxyy traffic over the last 7 days (throughput from streaming requests only); a model with too little traffic shows a dash. Benchmark scores appear only with their source and date. Oxyy is an independent API gateway, not affiliated with the model vendors named on this page.