modelbenchmark.io

Mixtral 8x22B

Mistral · mixtral-8x22b-instruct

Compare

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

Specification

most-agreed values

Context
66K
Max output
52K
Released
2024-04-17
Knowledge cutoff
2024-01-31
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.00
Output
$6.00
Cache read
$0.20

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nscale$0.60$0.60—————
fireworks_ai$1.20$1.20——66K66K—
vercel_ai_gateway · vercel-ai-gateway$1.20$1.20——66K2K—
kilo$2.00$6.00$0.20—66K52K—
nano-gpt$2.00$6.00$0.20—66K52K—
openrouter$2.00$6.00$0.20—66K52K—
aimlapi$2.116$6.348$0.2116—66K52K—
prime$2.20$6.60——66K52K—

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.20
2026-09-19openrouterCache read$0.20
2026-10-10openrouterCache read$0.20
2026-09-02openrouterInput$2.00
2026-09-06openrouterInput$2.00
2026-10-10openrouterInput$2.00
2026-09-02openrouterOutput$6.00
2026-09-06openrouterOutput$6.00
2026-10-10openrouterOutput$6.00
2026-10-13aimlapiCache read$0.2751
2026-10-23aimlapiCache read$0.2116
2026-10-13aimlapiInput$2.7508
2026-10-23aimlapiInput$2.116
2026-10-13aimlapiOutput$8.2524
2026-10-23aimlapiOutput$6.348

Other listings of this model

same model, different key

More from Mistral

most-hosted first