gpt-oss-20b es un modelo open-weight de 21B parámetros lanzado por OpenAI bajo la licencia Apache 2.0.
Los precios se actualizan automáticamente; se verifican a diario contra las tarifas oficiales de los proveedores.
Independent benchmark scores for gpt-oss-20b (batch), measured by Artificial Analysis. Higher is better. Modo de medición: High.
gpt-oss-20b (batch) is an open-weight AI model by OpenAI. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
gpt-oss-20b (batch) es un modelo de lenguaje de IA de OpenAI. Es open-weight: puede descargarlo y ejecutarlo en su propio hardware, de forma gratuita. Obtiene 9 en el índice de inteligencia Artificial Analysis.
The weights are free and open — you can self-host gpt-oss-20b (batch) and pay nothing per token. If you prefer a hosted API, list prices are $0.02 per million input tokens and $0.11 per million output tokens.
Los benchmarks independientes de Artificial Analysis le dan GPQA 68.8%, MMLU-Pro 74.8%, Humanity's Last Exam 11%, Long Context Reasoning 34.7%, LiveCodeBench 77.7%, SciCode 38.9%, AIME 2025 89.3%, IFBench 65.1%, τ²-Bench 60.2%, τ-Bench Banking 7%, Terminal-Bench 13.9%, Terminal-Bench Hard 10.6%. Se utiliza particularmente para generación de código.
Genera aproximadamente 194.2 tokens por segundo, con una mediana 0.42s de retraso antes del primer token. Medido de forma independiente por Artificial Analysis.
Yes. gpt-oss-20b (batch) has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.