Google

Gemma 4 26B A4B

Released 2026-04-03

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...

You send / 1M

$0.076

tokens in

It replies / 1M

$0.255

tokens out

Memory

262K

tokens it can read at once

Typical request

Free

1,000 words in, 400 out

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
AkashML · fp4$0.070$0.24097%Read
Makora$0.070$0.240100%n/a
NextBit · bf16$0.076$0.255100%Read
PrimeIntellect · bf16$0.100$0.300100%n/a
CoreWeave · bf16$0.100$0.300100%Read
Cloudflare$0.100$0.300100%Read
Io Net · bf16$0.090$0.310100%Read
DekaLLM · bf16$0.060$0.33099%Read
DeepInfra · fp8$0.070$0.340100%Read
SiliconFlow · fp8$0.140$0.40095%Read
Venice · bf16$0.130$0.400100%Read
Parasail · bf16$0.130$0.400100%Read
Novita · bf16$0.130$0.400100%Read
Google$0.150$0.60094%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: image, text, video
  • Writes: text
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 236K tokens
  • Repeated text is billed at $0.043 per 1M (prompt caching)
  • Intelligence score: 16.7 / 100 (Artificial Analysis)

Similar models

Appears in

Estimate your monthly cost with Gemma 4 26B A4B →