LLM Open Weight

Gemma 4 31B

by Google

Prices last updated November 22, 2026

Google's Gemma 4 31B — largest dense open-weight Gemma 4 model, with image input and a 262K-token context window.

Parameters
27B
Context
262k
Providers
11
Cheapest Input
$0.090
Vision JSON Mode Streaming Chat / InstructVision

Price Comparison

Compare pricing across 11 providers serving Gemma 4 31B

Provider Input $/1M Output $/1M Context Speed TTFT Status
Infron
Infron
$0.090 ● $0.340 262k — — Live
OpenRouter
OpenRouter
$0.100 $0.340 — — — Live
Novita AI
Novita AI
$0.140 $0.400 — — — Live
Friendli AI
Friendli AI
$0.140 $0.400 262k — — Live
WaveSpeed AI
WaveSpeed AI
$0.140 $0.400 262k — — Live
NeuralWatt
NeuralWatt
$0.144 $0.420 262k — — Live
KE
Keln
$0.150 $0.460 — — — Live
DeepInfra
DeepInfra
$0.200 $0.400 262k — — Live
Runcrate
Runcrate
$0.221 $0.441 262k — — Live
Sambanova
Sambanova
$0.380 $1.15 262k — — Live
Fireworks AI
Fireworks AI
$0.900 $0.900 — — — Down
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Gemma 4 31B, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Overall
One score combining a model's results across many benchmarks, on a common scale.
144.1±2.4
#102 of 258
Gemma 4 31B IT
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
75.8%±6.0
#112 of 232
gemma-4-31b-it_minimal
Aug 2026
Math
Competition maths problems from the OTIS mock AIME exams (2024-2025).
73.3%±13.1
#105 of 215
gemma-4-31b-it_minimal
Aug 2026
Coding
Text Arena votes on coding prompts only.
1,502±15
1,408 votes
#83 of 421
Gemma 4 31B
Nov 2026
Human votes on web apps the models build from a prompt.
1,370±6
16,567 votes
#122 of 161
Gemma 4 31B
Nov 2026
Knowledge
Short factual questions answered without search, measuring what the model knows and whether it makes things up.
10.4%±1.9
#95 of 97
gemma-4-31b-it
Aug 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,452±7
6,121 votes
#84 of 426
Gemma 4 31B
Nov 2026
Vision
Human votes on answers to prompts that include images (style-controlled).
1,265±5
42,217 votes
#41 of 168
Gemma 4 31B
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Popular comparisons

Gemma 4 31B guides

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.