← Model list

Gemma 4 31B IT

google·google/gemma-4-31b-it·BETA·Open weights·gemma series

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

At a glance
Official pricePrice undisclosed
Lowest paid$0.08 / $0.35
Kilo Gateway Gateway · 12.4× spread
5 more $0 channels
Context262,144
⚠ Providers report 32,768–262,144; the table below is authoritative
Output limit32,768
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Knowledge cutoff2025-01
Released / updated2026-04-02 / 2026-04-02

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 29 providers23 with public prices · 5 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree256,00016,384
QVAC
gemma4-31b
GatewayFree262,14432,768
KenariGatewayFree262,14432,768
UnoRouter
gemma-4-31b-it:free
GatewayFree262,14432,768
RequestyGatewayFree262,1448,192
Kilo GatewayGateway$0.08$0.35$0.01262,144262,144
CrofAIGateway$0.10$0.30$0.02262,144262,144
DevPass (LLM Gateway)Gateway$0.102$0.297$0.012262,14432,768
OpenRouterGateway$0.10$0.34$0.10262,144262,144
LilacGateway$0.11$0.35262,100262,100
GoogleOfficialFirst-party262,14432,768hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1DevPass (LLM Gateway)$24.45
2Kilo Gateway$25.10
3CrofAI$25.40
4NEAR AI Cloud$33.52
5OpenRouter$37.00
6Lilac$39.50

5 more channels offer $0 (Nvidia, QVAC, Kenari etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokenseffort = minimaleffort = xhigh

9 / 29 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.15$02026-08-052026-08-132026-08-05 · Min blended $0.152026-08-06 · Min blended $0.152026-08-07 · Min blended $0.152026-08-08 · Min blended $0.152026-08-09 · Min blended $0.1472026-08-10 · Min blended $0.1472026-08-11 · Min blended $0.1472026-08-12 · Min blended $0.1472026-08-13 · Min blended $0.147