Model comparison
Magnum V2 72B vs Magnum v4 72B
Compare Magnum V2 72B and Magnum v4 72B: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Anthracite Org
Magnum V2 72B
Open Llama instruction model for multilingual chat, reasoning, and coding
Anthracite Org
Magnum v4 72B
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://o
| Metric | Magnum V2 72B | Magnum v4 72B |
|---|---|---|
| Provider | Anthracite Org | Anthracite Org |
| Context window | 16,384 | 32,768 |
| Input $/Mtok | $2.01 | $3.00 |
| Output $/Mtok | $2.99 | $5.00 |
| Modalities | text | text |
| License | closed | open-weights |
Quick take
On input price, Magnum V2 72B is cheaper at $2.01/Mtok. For context window, Magnum v4 72B leads with 32,768 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.