Skip to content
llmwaves

Inference provider

Mistral

14 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.

Models served

14

Median output speed

48 t/s

Median latency

510ms

Median price / 1M

$0.6

Catalogue

Strongest and fastest on this provider

What the catalogue looks like at the top end, on the two axes that usually decide the choice.

Highest Intelligence Index

Among models this provider serves

View as table
ModelIntelligence
Mistral Medium 3.5 (Mistral AI)30.4
Mistral Medium 3.1 (Mistral AI)14.7
Mistral Medium 3 (Mistral AI)12.5
Mistral Large 2407 (Mistral AI)7.0
Saba (Mistral AI)6.2
Mistral Large (Mistral AI)4.1
Mixtral 8x22B Instruct (Mistral AI)4.0

Fastest output

Median tokens per second

View as table
ModelTokens/s
Voxtral Small 24B 2507 (Mistral AI)103
Mistral Small 4 (Mistral AI)102
Mixtral 8x22B Instruct (Mistral AI)101
Saba (Mistral AI)62
Ministral 3 14B 2512 (Mistral AI)61
Mistral Medium 3.1 (Mistral AI)51
Codestral 2508 (Mistral AI)49
Mistral Large 2407 (Mistral AI)47
Ministral 3 3B 2512 (Mistral AI)45
Mistral Large 3 2512 (Mistral AI)44

Full catalogue

All 14 models on Mistral

Filter by creator
14 of 14 models
Mistral Medium 3.5
Mistral AI
30.4$0.68
Mistral Medium 3.1
Mistral AI
14.7$0.07
Mistral Medium 3
Mistral AI
12.5$0.07
Mistral Large 2407
Mistral AI
7.0$0.25
Saba
Mistral AI
6.2$0.03
Mistral Large
Mistral AI
4.1$0.25
Mixtral 8x22B Instruct
Mistral AIopen
4.0$0.25
Mistral Small 4
Mistral AIopen
$0.06
Ministral 3 14B 2512
Mistral AIopen
$0.02
Ministral 3 8B 2512
Mistral AIopen
$0.01
Ministral 3 3B 2512
Mistral AIopen
$0.008
Mistral Large 3 2512
Mistral AI
$0.06
Voxtral Small 24B 2507
Mistral AIopen
$0.01
Codestral 2508
Mistral AI
$0.04