·
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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
| 信号 | 强度 | 权重 | 影响 |
|---|---|---|---|
| Benchmarksjust now | 61 | 30% | +18.2 |
| Recencyjust now | 91 | 15% | +13.6 |
| Capabilitiesjust now | 67 | 20% | +13.3 |
| Context Windowjust now | 81 | 10% | +8.1 |
| Output Capacityjust now | 20 | 10% | +2.0 |
| Pricingjust now | 0 | 15% | +0.0 |
社区和从业者反馈在基准测试和价格之上增加了真实世界的信号。
Share your experience with gpt-oss-120b and help the community make better decisions.
成本估算器
每月比类别平均节省$41.70
来自已验证的来源。