modelbenchmark.io

Mistral Nemo Instruct 2407

Mistral · mistral-nemo-instruct

Compare

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

Specification

most-agreed values

Context
131K
Max output
66K
Released
2024-07-18
Knowledge cutoff
2024-07
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.02
Output
$0.04
Cache read
$0.0257

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.019$0.03——131K131K—
meganova$0.02$0.04——131K66K—
nebius$0.04$0.12——128K128K—
io-net$0.0514$0.082$0.0257—128K4K—
nano-gpt$0.1003$0.1207$0.0502—16K8K—
ovhcloud · ovhcloud$0.13$0.13——118K118K—
ovhcloud$0.14$0.14——66K66K—
cortecs$0.145$0.145$0.014—118K118K—
fireworks_ai$0.20$0.20——128K128K—
gradient_ai · gradient-ai$0.30$0.30——128K1K—

Price history

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

DateHostField$/M
2026-09-02io-netCache read$0.01
2026-10-22io-netCache read$0.0257
2026-09-02io-netInput$0.02
2026-10-22io-netInput$0.0514
2026-09-02io-netOutput$0.04
2026-10-22io-netOutput$0.082

More from Mistral

most-hosted first