GPT OSS 120B · deepinfra

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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Leia também: Preços da API gpt-oss: gpt-oss-120b e gpt-oss-20b em todos os provedores

Todos os modelos OpenAI em todos os provedores

Entrada, $/1M $0.037

Saída, $/1M $0.17

Contexto 131 072

Saída máx. 16 384

Aceita texto

Última verificação 04.11.2026 12:00:14 UTC

Fonte —