As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gpt-oss-120b/

# gpt-oss-120b

OpenAI, gpt-oss family. Status: current. Type: reasoning model. Released: 2025-08-05. Training cutoff: 2024-06.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face |  |  | https://huggingface.co/openai/gpt-oss-120b |
| OpenAI API (docs) | `gpt-oss-120b` | https://api.openai.com/v1/responses | https://developers.openai.com/api/docs/models/gpt-oss-120b |
| Azure OpenAI (Microsoft Foundry) | `gpt-oss-120b` |  | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure |
| OpenRouter | `openai/gpt-oss-120b` |  | https://openrouter.ai/openai/gpt-oss-120b |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: text
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Open weights: yes
- Licence: apache-2.0

## What it has not seen

- Published training cutoff: 2024-06 (June 2024).
- AI events after it on Post-Cutoff: 2,060 (490 major, 98 historic), as of 2026-11-13.
- Already missing at launch: 51.
- Briefings of the news since June 2024: https://postcutoff.com/briefings/cutoff-2024-06-s.md (short), https://postcutoff.com/briefings/cutoff-2024-06-m.md (medium), https://postcutoff.com/briefings/cutoff-2024-06.md (full).
- Its card, with five things it has never heard of: https://postcutoff.com/you/gpt-oss-120b/

## What stands out

- Single-GPU open MoE: 117B total / 5.1B active MoE with MXFP4 weights; runs on one 80GB H100/MI300X. Source: https://huggingface.co/openai/gpt-oss-120b
- Open reasoning with full CoT: Configurable low/medium/high reasoning with full chain-of-thought access, harmony format. Source: https://huggingface.co/openai/gpt-oss-120b

## Notes

Open weights (Apache 2.0). OpenRouter from ~$0.04/$0.17 per 1M (provider-dependent). No first-party OpenAI pricing listed.

Self-hosted reasoning/agents via vLLM, Transformers, Ollama, LM Studio.

```bash
vllm serve openai/gpt-oss-120b
```

Sources:
- https://huggingface.co/openai/gpt-oss-120b
- https://developers.openai.com/api/docs/models/gpt-oss-120b
- Models overview: https://developers.openai.com/api/docs/models

Model page: https://postcutoff.com/m/gpt-oss-120b/