About
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
Related Models
Pricing
Input
$0.40
per 1M tokens
Output
$2.00
per 1M tokens
Blended
$0.80
per 1M tokens
Cheaper than 42% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.80
Monthly
$24.00
vs. Similar Models
Gemma 4 E4B (Reasoning)Q:0.0
$0.54-33%
DeepSeek R1 (Jan '25)Q:+0.1
$2.43+204%
Devstral MediumQ:-0.1
$0.800%
Llama Nemotron Super 49B v1.5 (Reasoning)Q:-0.1
$0.17-78%
Performance
48
tokens/sec
Faster than 16% of models
0.58
seconds
Faster than 80% of models
0.58
seconds
Faster than 86% of models
Market Median
94 tok/s
49% slower
Median TTFT
1.10s
48% faster
Throughput/Dollar
60
tok/s per $/1M
Speed Comparison
Qwen2.5 Max
48 tok/s+0%
Claude Sonnet 4.6 (Non-reasoning, Low Effort)
48 tok/s-1%
Qwen: Qwen3.7 Plus
47 tok/s-1%
Context Window
131K
tokens
Larger than 27% of models
Benchmarks
MMLU-Pro
76.0%
GPQA Diamond
57.8%
HLE
4.3%
LiveCodeBench
40.0%
SciCode
33.1%
TerminalBench Hard
3.8%
MATH-500
90.7%
AIME
44.0%
AIME 2025
30.3%
IFBench
39.3%
Long Context Recall
28.0%
Tau2
24.3%
Market AverageTop Score