gpt-oss-120b (batch)

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.

ChatOpenAI131k tokens$0.1635 / $0.654 · 1M

openai/gpt-oss-120b:batch

Contexto
131k tokens
Máx. completion
117,964
Tools
Sí
JSON
Sí
Lanzamiento
2025-08-05

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-120b:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es gpt-oss-120b (batch)?
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. gpt-oss-120b (batch) corre en el API de Geek Hub (compatible con OpenAI). Id: openai/gpt-oss-120b:batch.
¿gpt-oss-120b (batch) es gratis?
No. El input cuesta $0.1635 / 1M tokens y el output $0.654 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de gpt-oss-120b (batch)?
gpt-oss-120b (batch) tiene una ventana de 131k tokens. Soporta hasta 117,964 tokens de completion.
¿gpt-oss-120b (batch) soporta tool calling y structured outputs?
gpt-oss-120b (batch) acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó gpt-oss-120b (batch)?
gpt-oss-120b (batch) se lanzó el 5 de agosto de 2025.

Más modelos de OpenAI