gpt-oss-120b
OpenAI’s Apache-2.0 open-weight reasoning model; runs on a single 80GB GPU.
gpt-oss-120b is an open-weight, 117B-parameter mixture-of-experts model from OpenAI designed for high-reasoning, agentic and general-purpose production use. It activates 5.1B parameters per forward pass.
- Provider
- OpenAI
- Type
- Language model
- Released
- Aug 5, 2025
- Context window
- 131K tokens
- Max output
- 118K tokens
- Price
- $0.037 input / $0.17 output per 1M tokens
- Input
- text
- Output
- text
- Open weights
- Yes
- License
- Apache 2.0
Best for
- Local & on-device
- Reasoning
- Agents
- High volume / low cost
- Coding
Strengths
- Permissive Apache 2.0 license
- Extremely cheap via hosted providers
- Self-hostable
More from OpenAI
- GPT-6 Astra — OpenAI. OpenAI’s flagship for deep research, science and end-to-end engineering.
- GPT-6.1 Sol — OpenAI. Mid-tier GPT-6 model with excellent cost per task for agentic coding.
- GPT-6 Luna — OpenAI. Fast, cost-efficient GPT-6 tier for chat, classification and light agents.
- GPT-5.6 Terra — OpenAI. Balanced GPT-5.6 model for everyday coding and reasoning.
- gpt-oss-20b — OpenAI. Compact open-weight reasoning model that runs on consumer hardware.
- GPT-5.4 Image 2 — OpenAI. OpenAI’s native image generation and editing model.
- text-embedding-3-large — OpenAI. OpenAI’s most capable embedding; the default in countless RAG stacks.
- text-embedding-3-small — OpenAI. Cheap, fast OpenAI embedding for high-volume indexing.