GPT-OSS 120B.
OpenAI's first open-weight LLM in years — Apache-licensed MoE.
1× Nvidia H100 NVL.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 57.5 | 8629 ms | 8700 ms |
Smaller models distilled from GPT-OSS 120B.
Lightweight student models trained to mimic GPT-OSS 120B's outputs.
Variants in the GPT-OSS family.
Frequently asked.
How do I run GPT-OSS 120B?
Where can I access GPT-OSS 120B?
How much does it cost to run GPT-OSS 120B?
Is GPT-OSS 120B open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
384 GB | — | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
192 GB | — | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
80 GB | — | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for GPT-OSS 120B across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like GPT-OSS 120B, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About GPT-OSS 120B.
GPT-OSS 120B is OpenAI's surprise mid-2025 return to open-weights. MoE architecture, Apache-2.0 licensed. Trained with the same alignment stack as GPT-4o. Practical replacement for closed-API workloads where on-prem deployment matters.
How it's built.
How much it can remember.
What it can do.
Every place this model is hosted.
OpenAI API
api directPricing inferred from OpenRouter (within ~5-20% of direct API rates).