Model guide · prices from 2026-09-10 · API prices daily, full survey weekly

Cheapest way to run gpt-oss-120b (117B MoE)

gpt-oss-120b (117B MoE) needs ≈70 GB of VRAM at 4-bit — this week that starts at $0.91/hour (1× A100-SXM, cheapest tracked walk-up price). FP8 and FP16 below. VRAM calculators stop at the memory number; this connects it to live, graded prices across 20 providers.

MoE note: gpt-oss-120b (117B MoE) activates ~5.1B active per token, but the full 117B weights must fit in VRAM — memory scales with total parameters, speed with active ones.

FP16 — ≈281 GB needed

FP8/INT8 — ≈140 GB needed

4-bit — ≈70 GB needed

Method: VRAM ≈ parameters × bytes/parameter × 1.2 (20% headroom for KV cache and activations at ~8K context). Longer context or high concurrency needs more; training needs far more (optimizer states: ~4–8× weights). GPU counts assume even sharding. Above one 8-GPU node, the interconnect becomes the constraint — restrict to Grade A/B listings. Grades measure what sellers publish — deliverability of the written claim, not measured performance. No fleet holds a measured (Verified) badge yet; that tier arrives with the verification harness. Prices are this week's cheapest tracked walk-up listings (teaser prices excluded); every listing with grades and sources on the GPU pages. Interactive version for any model size: Model Fit.