Compare models
Up to 4 models side by side.
Provider | OpenAI |
|---|---|
Listed Date added to OpenRouter | Aug 5, 2025 |
Input price USD per 1M tokens | $0.09 |
Output price USD per 1M tokens | $0.36 |
Workload cost Chat reply (2K in, 500 out) | $0.0004 |
Context window | 131K |
Max output | 118K |
Output speed tokens per second | 211 |
Time to first token seconds | 1.38s |
Intelligence Index Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations. | 3.8 |
Engineering Index Artificial Analysis Engineering Index: engineering and technical problem solving. | 11.2 |
Inputs | text |
Open weights | Yes |
Good at | open-weightslow-cost |
Notes | 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. |
Best value in each row is highlighted. Share this page's URL to share the comparison.