ModelPickr

Models / Mistral / Devstral 2

Mistral · devstral

Devstral 2

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

$0.40 in · $2.00 out

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

Provider input prices run from $0.40 to $0.61 per 1M tokens. Output prices run from $2.00 to $3.03.

Context
262,144
Max output
262,144
Cache read
—
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Dec 9, 2025
Updated in source
Dec 9, 2025
Knowledge
2025-12
Providers
15

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.

Estimated monthly cost

Devstral 2

$5.40

Cache hit is ignored because this model has no cache-read price.

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
Amazon Bedrock$0.40$2.00———
DevPass$0.40$2.00——deprecated
Eden AI$0.40$2.00$0.04——
Kilo Gateway$0.40$2.00$0.04——
LLM Gateway$0.40$2.00———
Merge Gateway$0.40$2.00$0.04——
Mistralreference$0.40$2.00——deprecated
OpenRouter$0.40$2.00$0.04——
Opper$0.40$2.00———
Pioneer$0.40$2.00$0.40$0.40—
Cortecs$0.48$2.39$0.045——
GreenPT$0.57$2.74———
AI/ML API$0.61$3.03$0.061——
AnyAPI————deprecated
InferX$0$0———

Jobs this model qualifies for