modelbenchmark.io

Mistral Nemo

Mistral · mistral-nemo-instruct

Compare

12B parameter model with multilingual support.

Specification

most-agreed values

Context
16K
Max output
8K
Released
2024-01-01
Knowledge cutoff
2024-07
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.1003
Output
$0.1207
Cache read
$0.0502
Cache write
$0.02

Available from 12 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.019$0.03131K131K
io-net$0.02$0.04$0.01$0.04128K4K
meganova$0.02$0.04131K66K
pioneer$0.02$0.03$0.02$0.02128K128K
nebius$0.04$0.12128K128K
nano-gpt$0.1003$0.1207$0.050216K8K
ovhcloud · ovhcloud$0.13$0.13118K118K
ovhcloud$0.14$0.1466K66K
cortecs$0.145$0.145$0.014128K128K
fireworks_ai$0.20$0.20128K128K
digitalocean$0.30$0.30128K16K
gradient_ai · gradient-ai$0.30$0.30128K1K

Other listings of this model

same model, different key

More from Mistral

most-hosted first