Google: Gemma 4 31B

google/gemma-4-31b-it

Gemma 4 31B is a 31B open-weight model, ranking #114 of 262 on the TryAii Score. Its best showing is #18 on IFBench. It's served by 12 independent hosts from $0.2/$0.4 per million input/output tokens — about a third of what models at its level usually charge.

Prompt $/1M

$0.200

Completion $/1M

$0.400

Context

262,144 tok

Best provider

179 tok/s · ModelRun

Specs

Model id: google/gemma-4-31b-it
Display name: Google: Gemma 4 31B
Modality: text+image+video->text
Tokenizer: Gemma
Instruct type: —
Context length: 262,144
Max completion: 16,384
Prompt $/1M: $0.200
Completion $/1M: $0.400
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
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
ModelRunfastest	179	143 ms	205 ms
Friendli	103	923 ms	1,281 ms
SambaNova	50	3,055 ms	4,137 ms
Crusoe	46	510 ms	673 ms
CoreWeave	45	382 ms	541 ms
Novita	37	817 ms	994 ms
Artificial Analysis	35	1,000 ms	—
Venice	35	644 ms	784 ms
Io Net	30	709 ms	1,630 ms
Parasail	24	1,338 ms	1,862 ms
DeepInfra	24	614 ms	1,007 ms
Chutes	16	2,685 ms	3,461 ms
SiliconFlow	12	1,098 ms	1,557 ms