modelbenchmark.io

Devstral Small

Mistral · devstral-small

Compare

Legacy model retained for compatibility with older integrations

Specification

mistral listing

Context
128K
Max output
128K
Released
2025-07-10
Knowledge cutoff
2024-12
Retires
2025-11-30
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · mistral list price

Input
$0.10
Output
$0.30
Cache read
$0.03
Cache write
$0.10

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.10$0.30
128K
256K
128K
256K
2025-11-30
2026-05-31
io-net$0.05$0.22$0.025$0.10128K4K
nano-gpt$0.06$0.06$0.0333K8K
vercel_ai_gateway · vercel-ai-gateway$0.07$0.28128K128K
merge-gateway$0.10$0.30128K128K
fireworks_ai$0.90$0.90131K131K

More from Mistral

most-hosted first