# OpenAI: gpt-oss-120b (batch)

Provider: openai  
Category: llm  
Model ID: `openai/gpt-oss-120b:batch`

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

## Specs

- Context length: 131072 tokens
- Max output: 117964 tokens
- Modalities: text
- Released: 2025-08-05

## Pricing

- Input: $0.15 per million tokens
- Output: $0.60 per million tokens

---
Last verified: 2026-09-04T02:00:56.012Z  
Canonical URL: https://switchy.build/directory/models/gpt-oss-120b-batch