O1
Economy

OpenAI: gpt-oss-120b

by openai

The OpenAI: gpt-oss-120b is a powerful open-weight, 117B-parameter Mixture-of-Experts (MoE) language model. It's engineered for high-reasoning, agentic, and general-purpose production use cases, activating 5.1B parameters per forward pass. This model is optimized to run efficiently on a single H100 GPU, leveraging native MXFP4 quantization for superior performance. Key features include configurable reasoning depth, full chain-of-thought access, and native tool use capabilities. This encompasses robust function calling, advanced browsing, and precise structured output generation. With a generous 131K token context window and a 4K token max output, gpt-oss-120b is ideal for complex conversational AI and agentic workflows. Pricing is competitive at $0.04 per 1M input tokens and $0.19 per 1M output tokens, available on a FREE access tier. Explore its capabilities for your next project!

Large Language ModelMoEOpen-weight AIAgentic AIText Generation
87%Quality
131KContext Window
70%Speed
Category
Economy
API access
Unified context
RAG + Knowledge Base
24/7 Support
Try This ModelCompare models

Best For

Chat
Complex Reasoning
Agentic Workflows

🚀 Capabilities

Function Calling
Code Generation
Streaming Output

Limitations

No image generation

Specifications

Provideropenai
Context Window131,072 tokens
Max Output4,096 tokens
Minimum PlanEconomy

Pricing

Input Price$0.0390 / 1M tokens
Output Price$0.1900 / 1M tokens

💡 With PRO subscription, cost is reduced by 20%

Ready to try OpenAI: gpt-oss-120b?

Get 1,000 tokens free on signup

Start for free