Skip to main content
Back to Explore

Mistral Small 4 (Non-reasoning)

Mistral·Released 2026-03-16
Open SourceMultimodal

Pricing

Input

$0.15

per 1M tokens

Output

$0.60

per 1M tokens

Blended

$0.26

per 1M tokens

Cheaper than 65% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.26

Monthly

$7.86

vs. Similar Models

Devstral MediumQ:0.0
$0.80+205%
Llama Nemotron Super 49B v1.5 (Reasoning)Q:0.0
$0.17-33%
Gemma 4 E4B (Reasoning)Q:+0.1
$0.54+105%
Mistral: Mistral Medium 3Q:+0.1
$0.80+205%

Performance

149

tokens/sec

Faster than 73% of models

0.55

seconds

Faster than 83% of models

0.55

seconds

Faster than 88% of models

Market Median

94 tok/s

57% faster

Median TTFT

1.11s

50% faster

Throughput/Dollar

567

tok/s per $/1M

Speed Comparison

Qwen3.6 35B A3B (Non-reasoning)
149 tok/s+0%
Apertus 8B Instruct
148 tok/s-0%
GLM-4.7-Flash (Non-reasoning)
148 tok/s-1%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
57.1%
HLE
3.7%
LiveCodeBenchNot evaluated
SciCode
28.1%
TerminalBench Hard
10.6%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
32.8%
Long Context Recall
21.3%
Tau2
18.4%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models