modelbenchmark.io

Magistral Small 2506

Mistral · magistral-small

Compare

Mistral reasoning model for transparent analysis, math, and complex decisions

Specification

mistral listing

Context
262K
Max output
262K
Released
2025-06-10
Knowledge cutoff
2025-01
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.15
Output
$0.60
Cache read
$0.015
Cache write
$1.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock_converse$0.25
Batch outputbedrock_converse$0.75
Priority inputbedrock_converse$0.88
Priority outputbedrock_converse$2.63

Batch input is 50% below the interactive input price at the same listing.

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.15$0.60$0.015—262K262K—
nvidiafreefree——33K33K—
amazon-bedrock$0.50$1.50——128K40K—
bedrock_converse$0.50$1.50——128K40K—
io-net$0.50$1.50$0.25$1.00128K4K—
vercel_ai_gateway · vercel-ai-gateway$0.50$1.50——128K64K—

Price history

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

DateHostField$/M
2026-09-02mistralInput$0.50
2026-09-04mistralInput$0.50
2026-09-23mistralInput$0.50
2026-09-29mistralInput$0.15
2026-09-02mistralOutput$1.50
2026-09-04mistralOutput$1.50
2026-09-23mistralOutput$1.50
2026-09-29mistralOutput$0.60

More from Mistral

most-hosted first