# Magnum v4 72B API prices

Magnum v4 72B (llama) — 33k context, 8k max output.
3 metered per-token offers from 3 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $2.006 | $2.992 | $1.003 | 16k |
| Kilo Gateway | $2.5 | $5 | — | 33k |
| OpenRouter | $2.5 | $5 | — | 33k |

## Summary

- Cheapest input: $2.006 per 1M tokens (NanoGPT)
- Cheapest output: $2.992 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-10-22
- Inputs: pdf, text

## FAQ

### What is the cheapest Magnum v4 72B API?

As of Oct 4, 2026, NanoGPT has the lowest Magnum v4 72B output price at $2.992 per 1M tokens, and NanoGPT has the lowest input price at $2.006 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Magnum v4 72B?

3 providers list Magnum v4 72B on Sovyron; 3 of them sell it at a metered per-token price.

### Is Magnum v4 72B free?

No provider in the Sovyron catalog lists a free tier for Magnum v4 72B.

### What is the context window of Magnum v4 72B?

Magnum v4 72B supports a 33k-token context window and up to 8k output tokens.

HTML page: https://sovyron.com/models/magnum-v4-72b/
Full dataset: https://sovyron.com/data/catalog.json