OpenAI: gpt-oss-120b
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...
Everything else
| Max output | 131K |
|---|---|
| Input / 1M | $0.037 |
| Output / 1M | $0.17 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $0.207 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | always on · high, medium, low |
| Open weights | yes |
| Released | 2025-08-05 |
| Knowledge cutoff | 2024-06-30 |
| Retires | — |
| Catalog id | openai/gpt-oss-120b |
Benchmarks
| source | epoch |
|---|---|
| eci | 140.61 |
| confidence | Confident |
| accessibility | Open weights (unrestricted) |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.