OpenAI: gpt-oss-120b (batch)

The OpenAI gpt-oss-120b model is designed for handling text input, with a maximum context length of 131,072 tokens and a max completion token limit of 117,964. It supports tools and reasoning capabilities, making it suitable for applications that require these features. When considering the cost, this model charges $0.15 per million input tokens and $0.6 per million output tokens. Its blended benchmark score stands at 40.1 across three independent benchmarks, indicating solid performance. This makes it a viable option for users who need to integrate tools or reasoning capabilities into their applications, particularly those with large budgets or high-volume usage, as its pricing structure may be more manageable than competitors.