# gpt-oss-120b

`groq/openai/gpt-oss-120b` · OpenAI · text

OpenAI’s larger gpt-oss reasoning model runs on Groq. Its 131,072-token context can hold long documents, code and calculations.

[Model page](https://sociaro.com/models/groq/openai/gpt-oss-120b) · [JSON](https://sociaro.com/models/groq/openai/gpt-oss-120b.json) · [Model pricing](https://sociaro.com/pricing?model=groq%2Fopenai%2Fgpt-oss-120b) · [Documentation](https://docs.sociaro.com/models/groq-openai-gpt-oss-120b/)

## Use cases

- Trace a failing calculation across a long code sample
- Compare two technical proposals and explain where their assumptions differ

## Technical details

- API model ID — groq/openai/gpt-oss-120b
- Provider — OpenAI
- Modality — Text
- Input — Chat messages
- Output — Text
- Endpoint — POST /v1/chat/completions

## Request parameters

- `frequency_penalty`
- `logit_bias`
- `logprobs`
- `top_logprobs`
- `max_tokens`
- `max_completion_tokens`
- `modalities`
- `prediction`
- `n`
- `presence_penalty`
- `seed`
- `stop`
- `stream`
- `stream_options`
- `temperature`
- `top_p`
- `tools`
- `tool_choice`
- `function_call`
- `functions`
- `extra_headers`
- `parallel_tool_calls`
- `audio`
- `web_search_options`
- `service_tier`
- `safety_identifier`
- `prompt_cache_key`
- `prompt_cache_retention`
- `store`
- `response_format`
- `reasoning_effort`

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 0.18 per 1M input tokens · active
- USD 0.72 per 1M output tokens · active
- USD 0.09 per 1M cached input tokens · active
- USD 6 per 1K web searches · active

- Runs on Groq.
- Each page the search tool opens is billed $1.20 per 1K opens.

## Examples

### From brief to shot list

Two opening shots from an eight-second closed-course driving brief.

Shot 1. A wide elevated view establishes the track straight and the approaching red-and-white apex curb.

Shot 2. The car arrives at the entry line and its tail begins to swing outward, sending a short wedge of bright spray behind it.
