Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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...
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...
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| OpenAI: gpt-oss-120bopenai/gpt-oss-120b | OpenAI |
11.6 | 131.072K | $0.15 | $0.6 | 2025-08-05 | ||
| OpenAI: gpt-oss-20bopenai/gpt-oss-20b | OpenAI |
10.0 | 131.072K | $0.018 | $0.09 | 2025-08-05 |