openai
OpenAI gpt-oss-120b API price cut 84.7% input, 86.2% output on OpenRouter
Por ahora esta nota solo está disponible en inglés.
OpenAI's gpt-oss-120b model saw its OpenRouter API prices drop sharply on 2026-11-05, with input falling 84.7% to $0.023 per million tokens and output falling 86.2% to $0.083 per million tokens compared with 2026-11-04.
Precio en OpenRouter, por 1M de tokens
- 0,15 US$
- 0,60 US$
Price change details
Input price moved from $0.15 to $0.023 per million tokens, a decrease of 84.7%. Output price moved from $0.60 to $0.083 per million tokens, a decrease of 86.2%. The model offers a 131,072-token context window and has 116.8 billion parameters.
Model background
OpenAI announced the release of two open-weight models, gpt-oss-120b and gpt-oss-20b, under a permissive Apache 2.0 license. According to OpenAI, gpt-oss-120b has 117B parameters with 5.1B active parameters. The models were trained on the harmony response format and support configurable reasoning effort across low, medium, and high levels. Full chain-of-thought access is provided for debugging and trust. Models support fine-tuning for specialized use cases and have native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
Puntos clave
- OpenRouter input price for gpt-oss-120b fell 84.7% to $0.023 per million tokens.
- OpenRouter output price fell 86.2% to $0.083 per million tokens.
- OpenAI says MXFP4 quantization enables gpt-oss-120b to run on a single 80GB GPU like NVIDIA H100 or AMD MI300X.