# GPT-OSS 20B

> Canonical: https://www.overmindlab.ai/models/gpt-oss-20b

OpenAI gpt-oss 20B MoE mid-tier base when you want that architecture on Overmind.

| Property | Value |
| --- | --- |
| Model ID | openai/gpt-oss-20b |
| Provider | Open AI |
| Group | GPT-OSS |
| Parameters | 20B MoE |
| Tier | Mid |
| Context window | 128K |
| Max training context | 128K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $1.75 |
| Serving cost (per 1M output tokens) | from $12.00 |

## Overview

GPT-OSS 20B is available on Overmind for training on your agent's own traces, with benchmarking against your production model before any traffic moves.

GPT-OSS 20B is available on Overmind for training on your agent's own traces, with benchmarking against your production model before any traffic moves.

## Good for

- Mid-tier MoE experiments with OpenAI gpt-oss architecture
- Unsloth QLoRA training on agent traces

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md