Skip to main content
Back to Explore

Gemma 4 31B (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

Kimi K2.5 (Non-reasoning)Q:0.0
$1.20+485%
Qwen: Qwen3.5-35B-A3BQ:-0.1
$0.35+73%
Claude 4.5 Sonnet (Non-reasoning)Q:-0.1
$6.00+2827%
Qwen3.5 27B (Non-reasoning)Q:-0.1
$0.82+302%

Performance

36

tokens/sec

Faster than 5% of models

0.93

seconds

Faster than 60% of models

49.68

seconds

Faster than 8% of models

Market Median

93 tok/s

62% slower

Median TTFT

1.13s

17% faster

Throughput/Dollar

174

tok/s per $/1M

Speed Comparison

Claude 4 Opus (Non-reasoning)
35 tok/s-1%
Llama 3.1 Instruct 70B
35 tok/s-1%
Kimi K2.6 (Non-reasoning)
36 tok/s+2%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
85.7%
HLE
22.7%
LiveCodeBenchNot evaluated
SciCode
43.4%
TerminalBench Hard
36.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
75.6%
Long Context Recall
62.0%
Tau2
59.9%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models