LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemma 4 31B IT

google·google/gemma-4-31b-it·GA·Open weights·gemma series
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0 / $0
Blended $0 · Cache read —
Lowest paid·LLM GatewayGateway
$0.10 / $0.25
Blended $0.14 · 22.2× spread
11 more $0 channels
Context
262,144
Output limit
32,768
Knowledge cutoff
2025-01
Released / updated
2026-04-02 / 2026-04-02
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDFAudio
Weights
Hugging Face

Gemma 4 31B IT by google is offered by 59 providers on this page. Public prices are shown for 48 of them. Its official list price is $0 per 1M tokens. No paid channel is priced below the official list price. Prices vary about 22× across the providers that host it. It also has 11 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 4.4 on the Intelligence Index, with 11.9 for Engineering, its strongest domain. Against its lowest blended price of $0.138 per 1M, that is roughly 32 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 35 tokens per second, with 1.05s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 100,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, PDF, and Audio. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Reasoning

Intelligence4.4
Value32
Engineering11.9
Finance & Accounting8.2
Legal7.3
Strategy & Ops6.9
Economics9.5
Output speed35 tok/s
TTFT1.05 s
Value formulaIQ 4.4 ÷ min blended $0.138 = 32

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 59 providers48 with public prices · 11 free

  • ProviderInput / Output
  • GoogleOfficialFirst-party
    Free
    Context 262,144Output limit 32,768
  • QVACGateway
    gemma4-31b
    Free
    Context 262,144Output limit 32,768
  • RequestyGateway
    Free
    Context 262,144Output limit 8,192
  • AMDCloud
    Gemma-4-31B-IT
    Free
    Cache read $0Context 262,144Output limit 32,768
  • OpenRouterGateway
    google/gemma-4-31b-it:free
    Free
    Context 262,144Output limit 32,768
  • NvidiaCloud
    Free
    Context 256,000 ⚠Output limit 16,384
  • BothubGateway
    gemma-4-31b-it:free
    Free
    Context 262,144Output limit 32,768
  • AIHubMixGateway
    gemma-4-31b-it-free
    Free
    Context 262,144Output limit 32,768
  • PoeGateway
    google/gemma-4-31b
    Free
    Context 262,144Output limit 8,192
  • InferXGateway
    gemma-4-31B-it-fp8
    Free
    Context 262,144Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GoogleOfficialFirst-partyFree——262,14432,768
QVAC
gemma4-31b
GatewayFree——262,14432,768
RequestyGatewayFree——262,1448,192
AMD
Gemma-4-31B-IT
CloudFree$0—262,14432,768
OpenRouter
google/gemma-4-31b-it:free
GatewayFree——262,14432,768
NvidiaCloudFree——256,000 ⚠16,384
Bothub
gemma-4-31b-it:free
GatewayFree——262,14432,768
AIHubMix
gemma-4-31b-it-free
GatewayFree——262,14432,768
Poe
google/gemma-4-31b
GatewayFree——262,1448,192
InferX
gemma-4-31B-it-fp8
GatewayFree——262,14432,768

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.

Reasoning control

Toggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = maxeffort = xhighbudget_tokenseffort = minimal

Interleaved thinking (reasoning between tool calls) is declared by 11 of 59 providers.

15 / 59 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1LLM Gateway$21.70
2DevPass (LLM Gateway)$21.70
3LLM Gateway$24.45
4NanoGPT$29.54
5NanoGPT$29.54
6Chutes$29.54

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

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.15$02026-08-052026-11-18
2026-11-18Input list $0Output list $0Min blended $0.14

Artificial Analysis evaluations25 items

GPQA Diamond85.7%
Humanity's Last Exam23.6%
HLE-Diamond7.2%
MMMU-Pro73.4%
CritPt1.4%
CritPt v2 Hard4.0%
SciCode45.5%
FrontierCode 2.00.0%
Terminal-Bench Hard36.4%
Terminal-Bench 2.143.5%
Terminal-Bench 4.00.0%
Terminal-Bench-Science0.0%
τ²-Bench Telecom59.9%
τ³-Bench Banking14.8%
AutomationBench-AA4.9%
EnterpriseOps-Gym-AA28.3%
ITBench-AA37.3%
AA-Briefcase369
GDPval-AA627
GDP.pdf6.0%
AA-LCR69.7%
IFBench75.6%
AA-Omniscience Index-48.5
AA-Omniscience Accuracy19.9%
AA-Omniscience Non-Hallucination14.5%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Gemma 4 Uncensoredsame series—Gemma 4 12B Starry Oceansame series—Gemma 4 26B A4B Chimera X Hereticsame series—Gemma 4 31B Gembrain Uncensored Hereticsame lab—Gemma 4 E4B ITsame lab—
Data partly from models.dev (MIT) · Google official docs ↗