OpenAI: gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Everything else
| Max output | 131K |
|---|---|
| Input / 1M | $0.03 |
| Output / 1M | $0.13 |
| Cache read / 1M | $0.03 |
| Cache write / 1M | — |
| 1M in + 1M out | $0.16 |
| 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-20b |
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.