ModelPickr

Models / Mistral / Mistral Large 4

Mistral · mistral-large

Mistral Large 4

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

$0.68 in · $2.09 out

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

Provider input prices run from $0.68 to $1.36 per 1M tokens. Output prices run from $2.09 to $4.18.

Context
1,048,576
Max output
262,144
Cache read
$0.07
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Oct 6, 2026
Updated in source
Oct 6, 2026
Knowledge
—
Providers
9

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. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Mistralreference$0.68$2.09$0.07—beta
NanoGPT$0.68$2.09$0.07——
OpenCode$0.68$2.09$0.07——
Requesty$0.68$2.09$0.07——
LowRouter$0.71$2.19$0.073—beta
Cortecs$0.77$2.35$0.079——
DevPass$1.36$4.18$0.14——
LLM Gateway$1.36$4.18$0.14——
Ollama Cloud$1.36$4.18$0.14——

Jobs this model qualifies for