Skip to main content
Back to Explore

Mistral Small 3.1

Mistral·Released 2025-03-17
Open SourceMultimodal

Pricing

Input

$0.10

per 1M tokens

Output

$0.23

per 1M tokens

Blended

$0.14

per 1M tokens

Cheaper than 78% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.14

Monthly

$4.14

vs. Similar Models

Llama 3.3 Instruct 70BQ:0.0
$0.61+343%
OpenAI: GPT-4o (2024-05-13)Q:0.0
$7.50+5335%
Qwen3 32B (Non-reasoning)Q:0.0
$0.26+88%
Llama Nemotron Super 49B v1.5 (Non-reasoning)Q:+0.1
$0.17+27%

Performance

161

tokens/sec

Faster than 76% of models

0.56

seconds

Faster than 83% of models

0.56

seconds

Faster than 88% of models

Market Median

94 tok/s

71% faster

Median TTFT

1.13s

51% faster

Throughput/Dollar

1168

tok/s per $/1M

Speed Comparison

Mistral Small (Feb '24)
161 tok/s+0%
Gemini 3 Pro Preview (high)
161 tok/s+0%
GPT-5.4 nano (Non-Reasoning)
160 tok/s-0%

Benchmarks

MMLU-Pro
65.9%
GPQA Diamond
45.4%
HLE
4.8%
LiveCodeBench
21.2%
SciCode
26.5%
TerminalBench Hard
7.6%
MATH-500
70.7%
AIME
9.3%
AIME 2025
3.7%
IFBench
29.9%
Long Context Recall
19.7%
Tau2
25.1%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models