modelbenchmark.io

Ministral 8B (latest)

Mistral · ministral-8b

Compare

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Specification

mistral listing

Context
128K
Max output
128K
Released
2024-10-01
Knowledge cutoff
2024-10
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.10
Output
$0.10
Cache read
$0.015

Quality

2 benchmarks · 1 source

Composite
6th
percentile of 334 scored models
Rank
314 / 334
±0.06 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
one configuration only
reasoning2nd1/4 bench
math11th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 514.9 ±0.7defaultEpoch AI2025-01-27
GPQA diamond27.1 ±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
$0.10
$0.15
$0.10
$0.15
$0.015
128K
262K
128K
262K
vercel$0.10$0.10128K128K
vercel_ai_gateway · vercel-ai-gateway$0.10$0.10128K4K
kilo$0.15$0.15$0.015262K210K
llmgateway$0.15$0.15262K8K
llmgateway-providers$0.15$0.15262K262K
nano-gpt$0.15$0.15$0.075262K33K
openrouter$0.15$0.15$0.015262K
210K
262K
cortecs$0.179$0.179$0.017256K256K

Price history

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

DateHostField$/M
2026-09-02cortecsInput$0.167
2026-09-15cortecsInput$0.179
2026-09-02cortecsOutput$0.167
2026-09-15cortecsOutput$0.179

More from Mistral

most-hosted first