gpt-oss-120b
OpenAI's gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts language model built for complex reasoning and agentic tasks. It is designed for general-purpose production use and features a large context window of 131,072 tokens.
gpt-oss-120b specs and pricing
- Provider: OpenAI
- Released: August 5, 2025
- Context window: 131K tokens
- Max output: 66K tokens
- Input: text
- Output: text
- Price: $0.15 input / $0.60 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What gpt-oss-120b is good at
- Complex reasoning tasks
- Agentic workflows
- General-purpose production applications
To-dos to try with gpt-oss-120b
- Analyze a complex multi-step project plan and identify potential bottlenecks.
- Draft a technical architecture document based on provided system requirements.
- Automate a sequence of tasks by using the model's tool-calling capabilities to interact with external APIs.
FAQ
- What is the primary architecture of gpt-oss-120b? It is a Mixture-of-Experts (MoE) language model that activates 5.1 billion parameters per forward pass.
- What types of data can this model process? This model is designed to accept text as input and generate text as output.
- How much does gpt-oss-120b cost? gpt-oss-120b costs $0.15 per million input tokens and $0.60 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.5 credits ($1 = 100 credits).
- What is the context window of gpt-oss-120b? gpt-oss-120b can read up to 131K tokens at once and write up to 66K tokens in one reply.
- Can I use gpt-oss-120b without coding? Yes. In todo.is you pick gpt-oss-120b as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.