Loading...
Loading...
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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Preço/1M
$0.00
1st mais barato
100% abaixo da mediana
Top 27%
Janela de Contexto
131K
145th maior
Top 63%
Entrada
$0.00
por 1M tokens
Saída
$0.00
por 1M tokens
Combinado
$0.00
por 1M tokens
Mais barato que 73% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$0.00
Mensal
$0.00
Janela de Contexto
131K
tokens
Maior que 37% dos modelos
Saída Máxima
131K
tokens
100% do contexto
Comparação de Janela de Contexto