About
Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...
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
Llama Nemotron Super 49B v1.5 (Reasoning)Q:0.0
$0.17-78%
Mistral Small 4 (Non-reasoning)Q:0.0
$0.26-67%
Gemma 4 E4B (Reasoning)Q:+0.1
$0.54-33%
Mistral: Mistral Medium 3Q:+0.1
$0.800%
Performance
64
tokens/sec
Faster than 32% of models
0.59
seconds
Faster than 77% of models
0.59
seconds
Faster than 84% of models
Market Median
94 tok/s
32% slower
Median TTFT
1.11s
47% faster
Throughput/Dollar
80
tok/s per $/1M
Speed Comparison
Apertus 70B Instruct
64 tok/s-0%
Qwen3 Coder 480B A35B Instruct
64 tok/s-0%
Gemma 3n E2B Instruct
64 tok/s-0%
Context Window
131K
tokens
Larger than 27% of models
Benchmarks
MMLU-Pro
70.8%
GPQA Diamond
49.2%
HLE
3.8%
LiveCodeBench
33.7%
SciCode
29.4%
TerminalBench Hard
9.1%
MATH-500
70.7%
AIME
6.7%
AIME 2025
4.7%
IFBench
29.9%
Long Context Recall
28.7%
Tau2
19.9%
Market AverageTop Score