> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-OSS 120B

> A low-cost, broad-utility model on Kyma for writing, general tasks, and budget-sensitive workloads.

## Overview

`gpt-oss-120b` is one of the cheapest strong general-purpose models in Kyma's active catalog. It is a good fit for writing-heavy and budget-sensitive workloads where you still want a larger model.

## Specs

| Field              | Value                                                       |
| ------------------ | ----------------------------------------------------------- |
| Model ID           | `gpt-oss-120b`                                              |
| Best for           | Writing, general intelligence, cheap larger-model workloads |
| Context window     | 128K                                                        |
| Max output tokens  | 8K                                                          |
| Input modalities   | Text                                                        |
| Output modalities  | Text                                                        |
| Tool calling       | Yes                                                         |
| Structured outputs | Yes                                                         |
| Prompt caching     | Yes                                                         |
| Speed              | Medium                                                      |
| Cost band          | Cheap                                                       |
| Release stage      | Stable                                                      |

## Use this when

* You want a large model at low cost.
* You care about writing, summarization, and general-purpose tasks.
* You want a budget-friendly model with a decent context window.

## Pick something else when

* You want stronger coding and reasoning quality: use [`qwen-3.6-plus`](/models/qwen-3.6-plus) or `deepseek-v3`.
* You need deep reasoning: use [`deepseek-r1`](/models/deepseek-r1).
* You need vision or multimodal input: use `gemma-4-31b` or [`kimi-k2.6`](/models/kimi-k2.6).

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Rewrite this landing page copy to be clearer and more persuasive."}]
)
```