Models / Mistral / Mistral Medium 3.5

Mistral · mistral-medium

Mistral Medium 3.5

Balanced Mistral model for enterprise assistants, multilingual work, and tools

$1.50 in · $7.50 out

per 1M tokens · first-party price. Reference price from Mistral, the lab's own listing.

Provider input prices run from $1.50 to $2.05 per 1M tokens. Output prices run from $6.90 to $10.26.

Context
262,144
Max output
262,144
Cache read
$0.15
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
Yes
License
—
Released
Apr 29, 2026
Updated in source
Apr 29, 2026
Knowledge
—
Providers
11

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Eden AI$1.50$7.50$0.15——
Mistralreference$1.50$7.50$0.15——
Pioneer$1.50$7.50$1.50$1.50—
Scaleway$1.50$7.50———
Tempr Gateway$1.50$7.50———
LowRouter$1.57$7.84$0.16——
evroc$1.73$6.90———
GreenPT$2.05$10.26———
Kenari$0$0———
Nvidia$0$0——deprecated
SAP AI Core—————

Jobs this model qualifies for