modelbenchmark.io

Mistral 7B Instruct v0.3

Mistral · mistral-7b-instruct

Compare

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Specification

most-agreed values

Context
33K
Max output
33K
Released
2023-04-30
Knowledge cutoff
Retires
2025-11-13
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.20
Cache read
$0.20
Cache write
$0.20

Rate limits

Requests per minute
300

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidiafreefree66K66K
perplexity$0.07$0.284K4K
openrouter$0.13$0.1333K8K
bedrock
$0.20
$0.15
$0.26
$0.20
32K8K
fireworks_ai$0.20$0.2033K33K
pioneer$0.20$0.20$0.20$0.2033K33K
together_ai$0.20$0.2033K2025-11-13
cloudflare$1.923$1.9238K8K

Other listings of this model

same model, different key

More from Mistral

most-hosted first