GPT-5.1-Codex-Max

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. GPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle.

ChatOpenAI400k tokens$1.3626 / $10.9006 · 1M

openai/gpt-5.1-codex-max

Contexto
400k tokens
Máx. completion
128,000
Tools
JSON
Lanzamiento
2025-12-04

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-5.1-codex-max",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es GPT-5.1-Codex-Max?
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic workflows spanning software engineering, mathematics, and research. GPT-5.1-Codex-Max delivers faster performance, improved reasoning, and higher token efficiency across the development lifecycle. GPT-5.1-Codex-Max corre en el API de Geek Hub (compatible con OpenAI). Id: openai/gpt-5.1-codex-max.
¿GPT-5.1-Codex-Max es gratis?
No. El input cuesta $1.3626 / 1M tokens y el output $10.9006 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de GPT-5.1-Codex-Max?
GPT-5.1-Codex-Max tiene una ventana de 400k tokens. Soporta hasta 128,000 tokens de completion.
¿GPT-5.1-Codex-Max soporta tool calling y structured outputs?
GPT-5.1-Codex-Max acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó GPT-5.1-Codex-Max?
GPT-5.1-Codex-Max se lanzó el 4 de diciembre de 2025.

Más modelos de OpenAI