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!
✅ Best For
🚀 Capabilities
❌ Limitations
Specifications
| Provider | openai |
| Context Window | 131,072 tokens |
| Max Output | 4,096 tokens |
| Minimum Plan | Economy |
Pricing
| Input Price | $0.0390 / 1M tokens |
| Output Price | $0.1900 / 1M tokens |
💡 With PRO subscription, cost is reduced by 20%