modelbenchmark.io

Mistral Nemo

Mistral · mistral-nemo

Compare

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Specification

mistral listing

Context
128K
Max output
128K
Released
2024-07-01
Knowledge cutoff
2024-07
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.15
Output
$0.15

Quality

2 benchmarks · 1 source

Composite
6th
percentile of 334 scored models
Rank
315 / 334
±0.06 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
one configuration only
reasoning4th1/4 bench
math7th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 510.8 ±0.6defaultEpoch AI2025-01-27
GPQA diamond29.9 ±2.1defaultEpoch AI2025-01-27

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.15$0.15128K128K
kilo$0.019$0.03131K16K
openrouter$0.019$0.03131K16K
novita$0.04$0.1760K16K
novita-ai$0.04$0.1760K16K
azure_ai$0.15$0.15131K4K
vercel$0.15$0.15128K128K
vertex_ai-mistral_models
$3.00
$0.15
$3.00
$0.15
128K128K
helicone$20.00$40.00128K16K

Price history

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

DateHostField$/M
2026-09-02openrouterInput$0.019
2026-09-06openrouterInput$0.019
2026-09-02openrouterOutput$0.03
2026-09-06openrouterOutput$0.03

Other listings of this model

this page is one of them

The corpus files Mistral Nemo under several keys. This page is the mistral-nemo listing. The full record — every host, every price and every benchmark score — is on the main Mistral Nemo page.

More from Mistral

most-hosted first