Skip to main content
Back to Explore

Gemma 4 31B (Non-reasoning)

Google·Released 2026-04-02
Open SourceMultimodal

Pricing

Input

$0.14

per 1M tokens

Output

$0.40

per 1M tokens

Blended

$0.20

per 1M tokens

Cheaper than 71% of models. Median price is $0.67/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.20

Monthly

$6.15

vs. Similar Models

Grok 4.20 0309 v2 (Non-reasoning)Q:0.0
$3.00+1363%
Nova 2.0 Pro Preview (medium)Q:0.0
$3.44+1577%
Gemma 4 12B (Reasoning)Q:+0.2
$0.15-27%
Grok Code Fast 1Q:-0.2
$0.53+156%

Performance

68

tokens/sec

Faster than 36% of models

0.65

seconds

Faster than 75% of models

0.65

seconds

Faster than 81% of models

Market Median

93 tok/s

26% slower

Median TTFT

1.13s

42% faster

Throughput/Dollar

334

tok/s per $/1M

Speed Comparison

Apriel-v1.6-15B-Thinker
69 tok/s+1%
Llama 3.2 Instruct 11B (Vision)
68 tok/s-1%
Qwen3 235B A22B 2507 (Reasoning)
67 tok/s-1%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
76.3%
HLE
11.5%
LiveCodeBenchNot evaluated
SciCode
41.1%
TerminalBench Hard
30.3%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
53.5%
Long Context Recall
36.0%
Tau2
65.5%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models