modelbenchmark.io

Mistral Small 3.1 24B (Cloudflare)

Mistral · mistral-small-3-1-24b-instruct

Compare

Efficient Mistral model for fast chat, extraction, and production assistants

Specification

most-agreed values

Context
131K
Max output
16K
Released
2025-03-17
Knowledge cutoff
2023-10-31
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.106
Output
$0.318
Cache read
$0.05

Rate limits

Requests per minute
300

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.10$0.30$0.05—128K102K—
watsonx$0.106$0.318——131K16K—
cloudflare$0.351$0.555——128K128K—
cloudflare-workers-ai · cf$0.351$0.555——128K128K—
edenai$0.351$0.555——128K102K—
kilo$0.351$0.555——128K102K—
openrouter$0.351$0.555——128K102K—
aimlapi$0.3714$0.5872——128K128K—

Price history

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

DateHostField$/M
2026-09-02openrouterInput$0.351
2026-09-06openrouterInput$0.351
2026-10-10openrouterInput$0.351
2026-09-02watsonxInput$0.106
2026-09-06watsonxInput$0.106
2026-09-02openrouterOutput$0.555
2026-09-06openrouterOutput$0.555
2026-10-10openrouterOutput$0.555
2026-09-02watsonxOutput$0.318
2026-09-06watsonxOutput$0.318
2026-10-13aimlapiInput$0.4828
2026-10-23aimlapiInput$0.3714
2026-10-13aimlapiOutput$0.7633
2026-10-23aimlapiOutput$0.5872

More from Mistral

most-hosted first