The honest, $0-markup cost to run gpt-oss-120b (OpenAI, 117B) and Llama 4 Scout (17B-16E) (Meta, 109B), side by side — free on your own machine, on your own rented GPU at the vendor's price, or via your own API key.
| gpt-oss-120b | Llama 4 Scout (17B-16E) | |
|---|---|---|
| Parameters | 117B | 109B |
| Context window | 131.1K | ✓ 1M |
| License | Commercial OK | Commercial OK |
| VRAM to run | ~80 GB (Q4_K_M) | ✓ ~77 GB (Q4_K_M) |
| Rent a GPU | $0.48/hr | $0.48/hr |
| Your API key | ✓ $0.09/1M | $0.20/1M (last-known) |
VRAM, size, context and license are facts from the catalog and the shared cost engine; API prices are real where we have them (labeled "est." otherwise). We don't rank model quality or quote benchmarks here.
Full cost breakdown: gpt-oss-120b →
Full cost breakdown: Llama 4 Scout (17B-16E) →
Open the free Spanvero advisor → to compare them live for your exact workload and hardware.
Spanvero · All comparisons · Prices as of 2026-07-06. $0 markup, your own accounts, we never resell compute. © 2026 Cynosure LLC.
A short email of real AI price moves, straight from the daily log — no hype. We're collecting the list now; the first issue goes out when it opens. Unsubscribe with one click.