modelbenchmark.io

Mixtral 8x7B Instruct v0.1 (Deep Infra)

Mistral · mixtral-8x7b-instruct

Compare

Open sparse mixture-of-experts Mistral instruction model

Specification

most-agreed values

Context
33K
Max output
33K
Released
2023-12-11
Knowledge cutoff
—
Retires
2027-03-30
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.40
Output
$0.40

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
perplexity$0.07$0.28——4K4K—
deepinfra$0.40$0.40——33K33K—
edenai$0.40$0.40——33K33K—
fireworks_ai$0.50$0.50——33K33K—
bedrock
$0.59
$0.45
$0.91
$0.70
——32K4K2027-03-30
together_ai$0.60$0.60——33K33K2026-04-16

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02together_aiInput$0.60
2026-09-24together_aiInput$0.60
2026-09-02together_aiOutput$0.60
2026-09-24together_aiOutput$0.60

More from Mistral

most-hosted first