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 #111 of 235 on the TryAii Score. Its best showing is #33 on IFBench. It's served by 13 independent hosts from $0.07/$0.34 per million input/output tokens — about a third of what models at its level usually charge.

Prompt $/1M

$0.070

Completion $/1M

$0.340

Context

262,144 tok

Best provider

76 tok/s · Wafer

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: 16,384
Prompt $/1M: $0.070
Completion $/1M: $0.340
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
Waferfastest	76	696 ms	750 ms
Artificial Analysis	70	704 ms	—
DekaLLM	47	1,194 ms	1,557 ms
Cloudflarefastest	44	464 ms	575 ms
SiliconFlow	37	1,271 ms	1,576 ms
Parasail	32	816 ms	1,047 ms
Google	32	366 ms	693 ms
NextBit	30	916 ms	1,124 ms
Ambient	27	698 ms	1,022 ms
Venice	23	966 ms	1,196 ms
Novita	23	793 ms	922 ms
Io Net	20	905 ms	1,639 ms
DeepInfra	18	336 ms	415 ms
Ionstream	7	1,627 ms	2,781 ms
Darkbloom	6	5,070 ms	6,004 ms
googlefastest	—	—	—