Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

Gemma 4 26B A4B is a 26B open-weight model (4B active per token), ranking #138 of 260 on the TryAii Score. Its best showing is #34 on IFBench. It's served by 12 independent hosts from $0.0675/$0.225 per million input/output tokens — about a quarter of what models at its level usually charge.

Prompt $/1M

$0.068

Completion $/1M

$0.225

Context

262,144 tok

Best provider

197 tok/s · Makora

Specs

Model id: google/gemma-4-26b-a4b-it
Display name: Google: Gemma 4 26B A4B
Modality: text+image+video->text
Tokenizer: Gemma
Instruct type: —
Context length: 262,144
Max completion: 235,929
Prompt $/1M: $0.068
Completion $/1M: $0.225
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Makorafastest	197	199 ms	332 ms
Io Net	71	524 ms	598 ms
Darkbloom	68	588 ms	787 ms
NextBit	65	277 ms	399 ms
Novita	62	767 ms	930 ms
DekaLLM	59	615 ms	799 ms
Artificial Analysis	52	664 ms	—
Parasail	52	911 ms	1,331 ms
DeepInfra	44	629 ms	873 ms
Cloudflare	42	528 ms	808 ms
Venice	35	1,358 ms	1,857 ms
Google	24	2,218 ms	2,881 ms
SiliconFlow	24	1,311 ms	1,611 ms
CoreWeave	20	271 ms	342 ms