Models / Anthracite / Magnum v4 72B

Anthracite

Magnum v4 72B

Open-weight instruction model for adaptable chat and self-hosted production workloads

$2.01 in · $2.99 out

per 1M tokens · provider rate closest to the median. No first-party Anthracite price was listed. The reference price is NanoGPT's rate, the provider closest to the median.

Provider input prices run from $2.01 to $4.13 per 1M tokens. Output prices run from $2.99 to $6.88.

Context
32,768
Max output
4,096
Cache read
$1.00
Cache write
—
Reasoning
No
Tool calls
No
Structured output
Yes
Vision
No
Open weights
Yes
License
—
Released
Oct 22, 2024
Updated in source
Oct 22, 2024
Knowledge
2024-06-30
Providers
2

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
NanoGPTreference$2.01$2.99$1.00——
AI/ML API$4.13$6.88———