Codex - Conectar el asistente de terminal de OpenAI a Model Studio - Alibaba Cloud Model Studio

Codex es el asistente de codificación AI de terminal de OpenAI. Conéctelo a Alibaba Cloud Model Studio mediante Token Plan Personal Edition, Token Plan Team Edition, Coding Plan o pago por uso.

Instalar Codex

Instale o actualice Node.js (v18.0 o posterior).
Instalar Codex:

npm install -g @openai/codex

Verifique la instalación:

codex --version

Configuración de credenciales de acceso

Edite ~/.codex/config.toml y configure la variable de entorno OPENAI_API_KEY para su plan de facturación:

Token Plan Personal Edition

Para model, seleccione un modelo admitido. Configure la variable de entorno OPENAI_API_KEY con la API KeyAPI Key dedicada de Token Plan Personal Edition.

Paso 1: Configurar variables de entorno

Establezca la variable de entorno OPENAI_API_KEY en la API Key dedicada de Token Plan Personal Edition.

macOS

Compruebe su shell predeterminada:

echo $SHELL

Establezca la variable de entorno según su tipo de shell:

Zsh

# Replace YOUR_API_KEY with the Token Plan Personal Edition API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc

Bash

# Replace YOUR_API_KEY with the Token Plan Personal Edition API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bash_profile

Aplique el cambio:

Zsh

source ~/.zshrc

Bash

source ~/.bash_profile

Windows

CMD

Establezca la variable de entorno:

REM Replace YOUR_API_KEY with the Token Plan Personal Edition API Key
setx OPENAI_API_KEY "YOUR_API_KEY"

Abra una nueva ventana de CMD para verificar:

echo %OPENAI_API_KEY%

PowerShell

Establezca la variable de entorno:

# Replace YOUR_API_KEY with the Token Plan Personal Edition API Key
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "YOUR_API_KEY", [EnvironmentVariableTarget]::User)

Abra una nueva ventana de PowerShell para verificar:

echo $env:OPENAI_API_KEY

Paso 2: Elegir un método de acceso

Elija un método de acceso según la API compatible con el modelo:

API Responses

Si el modelo seleccionado admite la API OpenAI Responses, puede usar la última versión de Codex.

model_provider = "Model_Studio_Token_Plan_Personal"
model = "auto"
[model_providers.Model_Studio_Token_Plan_Personal]
name = "Model_Studio_Token_Plan_Personal"
base_url = "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Luego configure los metadatos del modelo para cambiar entre modelos. Cree ~/.codex/model-catalog.local.json con los modelos admitidos por este plan:

{
  "models": [
    {
      "slug": "auto",
      "display_name": "auto",
      "description": "DashScope model: auto",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.8-max",
      "display_name": "qwen3.8-max",
      "description": "DashScope model: qwen3.8-max",
      "default_reasoning_level": "xhigh",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 983616,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.8-flash",
      "display_name": "qwen3.8-flash",
      "description": "DashScope model: qwen3.8-flash",
      "default_reasoning_level": "xhigh",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 983616,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 2,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.7-max",
      "display_name": "qwen3.7-max",
      "description": "DashScope model: qwen3.7-max",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 3,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.7-plus",
      "display_name": "qwen3.7-plus",
      "description": "DashScope model: qwen3.7-plus",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 4,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.6-flash",
      "display_name": "qwen3.6-flash",
      "description": "DashScope model: qwen3.6-flash",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 5,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.3",
      "display_name": "glm-5.3",
      "description": "DashScope model: glm-5.3",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 6,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.2",
      "display_name": "glm-5.2",
      "description": "DashScope model: glm-5.2",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 7,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4.1-flash",
      "display_name": "deepseek-v4.1-flash",
      "description": "DashScope model: deepseek-v4.1-flash",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 8,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4.1-flash-1017",
      "display_name": "deepseek-v4.1-flash-1017",
      "description": "DashScope model: deepseek-v4.1-flash-1017",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 8,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-pro",
      "display_name": "deepseek-v4-pro",
      "description": "DashScope model: deepseek-v4-pro",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 163840,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 9,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-pro-0813",
      "display_name": "deepseek-v4-pro-0813",
      "description": "DashScope model: deepseek-v4-pro-0813",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 163840,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 10,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-flash-0731",
      "display_name": "deepseek-v4-flash-0731",
      "description": "DashScope model: deepseek-v4-flash-0731",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 11,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    }
  ]
}

Añada lo siguiente a ~/.codex/config.toml para apuntar al archivo:

model_catalog_json = "~/.codex/model-catalog.local.json"

Después de configurar, cambie entre modelos con codex -m (por ejemplo, codex -m qwen3.8-flash), o ingrese /model en la TUI.

API Chat/Completions (otros modelos)

Otros modelos requieren la API Chat/Completions. Instale una versión anterior de Codex, como 0.80.0:

npm install -g @openai/codex@0.80.0

model_provider = "Model_Studio_Token_Plan_Personal"
model = "glm-5"
[model_providers.Model_Studio_Token_Plan_Personal]
name = "Model_Studio_Token_Plan_Personal"
base_url = "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

Token Plan Team Edition

Para model, seleccione un modelo admitido. Configure la variable de entorno OPENAI_API_KEY con la API KeyAPI Key dedicada de Token Plan Team Edition.

Paso 1: Configurar variables de entorno

Establezca la variable de entorno OPENAI_API_KEY en la API Key dedicada de Token Plan Team Edition.

macOS

Compruebe su shell predeterminada:

echo $SHELL

Establezca la variable de entorno según su tipo de shell:

Zsh

# Replace YOUR_API_KEY with the Token Plan Team Edition API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc

Bash

# Replace YOUR_API_KEY with the Token Plan Team Edition API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bash_profile

Aplique el cambio:

Zsh

source ~/.zshrc

Bash

source ~/.bash_profile

Windows

CMD

Establezca la variable de entorno:

REM Replace YOUR_API_KEY with the Token Plan Team Edition API Key
setx OPENAI_API_KEY "YOUR_API_KEY"

Abra una nueva ventana de CMD para verificar:

echo %OPENAI_API_KEY%

PowerShell

Establezca la variable de entorno:

# Replace YOUR_API_KEY with the Token Plan Team Edition API Key
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "YOUR_API_KEY", [EnvironmentVariableTarget]::User)

Abra una nueva ventana de PowerShell para verificar:

echo $env:OPENAI_API_KEY

Paso 2: Elegir un método de acceso

Elija un método de acceso según la API compatible con el modelo:

API Responses

Si el modelo seleccionado admite la API OpenAI Responses, puede usar la última versión de Codex.

model_provider = "Model_Studio_Token_Plan"
model = "auto"
[model_providers.Model_Studio_Token_Plan]
name = "Model_Studio_Token_Plan"
base_url = "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Luego configure los metadatos del modelo para cambiar entre modelos. Cree ~/.codex/model-catalog.local.json con los modelos admitidos por este plan:

{
  "models": [
    {
      "slug": "auto",
      "display_name": "auto",
      "description": "DashScope model: auto",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.8-max",
      "display_name": "qwen3.8-max",
      "description": "DashScope model: qwen3.8-max",
      "default_reasoning_level": "xhigh",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 983616,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.8-flash",
      "display_name": "qwen3.8-flash",
      "description": "DashScope model: qwen3.8-flash",
      "default_reasoning_level": "xhigh",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 983616,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 2,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.7-max",
      "display_name": "qwen3.7-max",
      "description": "DashScope model: qwen3.7-max",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 3,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.7-plus",
      "display_name": "qwen3.7-plus",
      "description": "DashScope model: qwen3.7-plus",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 4,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.6-flash",
      "display_name": "qwen3.6-flash",
      "description": "DashScope model: qwen3.6-flash",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 5,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.3",
      "display_name": "glm-5.3",
      "description": "DashScope model: glm-5.3",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 6,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.2",
      "display_name": "glm-5.2",
      "description": "DashScope model: glm-5.2",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 7,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4.1-flash",
      "display_name": "deepseek-v4.1-flash",
      "description": "DashScope model: deepseek-v4.1-flash",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 8,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4.1-flash-1017",
      "display_name": "deepseek-v4.1-flash-1017",
      "description": "DashScope model: deepseek-v4.1-flash-1017",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 8,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-pro",
      "display_name": "deepseek-v4-pro",
      "description": "DashScope model: deepseek-v4-pro",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 163840,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 9,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-pro-0813",
      "display_name": "deepseek-v4-pro-0813",
      "description": "DashScope model: deepseek-v4-pro-0813",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 163840,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 10,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-flash-0731",
      "display_name": "deepseek-v4-flash-0731",
      "description": "DashScope model: deepseek-v4-flash-0731",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 11,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.6-plus",
      "display_name": "qwen3.6-plus",
      "description": "DashScope model: qwen3.6-plus",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 12,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },


    {
      "slug": "kimi-k2.7-code",
      "display_name": "kimi-k2.7-code",
      "description": "DashScope model: kimi-k2.7-code",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 262144,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 15,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "kimi-k2.6",
      "display_name": "kimi-k2.6",
      "description": "DashScope model: kimi-k2.6",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 262144,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 16,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "kimi-k2.5",
      "display_name": "kimi-k2.5",
      "description": "DashScope model: kimi-k2.5",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 262144,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 17,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.1",
      "display_name": "glm-5.1",
      "description": "DashScope model: glm-5.1",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 202752,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 18,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5",
      "display_name": "glm-5",
      "description": "DashScope model: glm-5",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 202752,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 19,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "MiniMax-M2.5",
      "display_name": "MiniMax-M2.5",
      "description": "DashScope model: MiniMax-M2.5",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 204800,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 20,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    }
  ]
}

Añada lo siguiente a ~/.codex/config.toml para apuntar al archivo:

model_catalog_json = "~/.codex/model-catalog.local.json"

Después de configurar, cambie entre modelos con codex -m (por ejemplo, codex -m qwen3.8-flash), o ingrese /model en la TUI.

API Chat/Completions (otros modelos)

Otros modelos requieren la API Chat/Completions. Instale una versión anterior de Codex, como 0.80.0:

model_provider = "Model_Studio_Token_Plan"
model = "glm-5"
[model_providers.Model_Studio_Token_Plan]
name = "Model_Studio_Token_Plan"
base_url = "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

Plan de codificación

Para model, seleccione un modelo admitido. Configure la variable de entorno OPENAI_API_KEY con la API KeyAPI Key dedicada de Coding Plan.

Paso 1: Configurar variables de entorno

Establezca la variable de entorno OPENAI_API_KEY en la API Key dedicada de Coding Plan.

macOS

Compruebe su shell predeterminada:

echo $SHELL

Establezca la variable de entorno según su tipo de shell:

Zsh

# Replace YOUR_API_KEY with the Coding Plan API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc

Bash

# Replace YOUR_API_KEY with the Coding Plan API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bash_profile

Aplique el cambio:

Zsh

source ~/.zshrc

Bash

source ~/.bash_profile

Windows

CMD

Establezca la variable de entorno:

REM Replace YOUR_API_KEY with the Coding Plan API Key
setx OPENAI_API_KEY "YOUR_API_KEY"

Abra una nueva ventana de CMD para verificar:

echo %OPENAI_API_KEY%

PowerShell

Establezca la variable de entorno:

# Replace YOUR_API_KEY with the Coding Plan API Key
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "YOUR_API_KEY", [EnvironmentVariableTarget]::User)

Abra una nueva ventana de PowerShell para verificar:

echo $env:OPENAI_API_KEY

Paso 2: Configurar acceso

Coding Plan solo admite la API Chat/Completions. Configure de la siguiente manera:

API Chat/Completions

Coding Plan solo admite la API Chat/Completions. Instale una versión anterior de Codex, como 0.80.0:

model_provider = "Model_Studio_Coding_Plan"
model = "qwen3.7-plus"
[model_providers.Model_Studio_Coding_Plan]
name = "Model_Studio_Coding_Plan"
base_url = "https://coding-intl.dashscope.aliyuncs.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

Coding Plan no admite la API Responses (solo API Chat/Completions), por lo que los metadatos multimodelo no se configuran aquí. Para cambiar entre modelos, utilice Token Plan o la API Responses de pago por uso en su lugar.

Pago por uso

Configure OPENAI_API_KEY con su API KeyAPI Key de Model Studio y elija entre los modelos admitidos.

Configure base_url para su región. La API Key debe coincidir con la región seleccionada; reemplace {WorkspaceId} en la URL con su Workspace ID real:

Norte de China 2 (Beijing): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1
Singapur: https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1
EE. UU. (Virginia): https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/compatible-mode/v1

El modelo de pago por uso admite tanto la API Responses como la API Chat/Completions. Elija según su modelo:

Paso 1: Configurar variables de entorno

Configure la variable de entorno OPENAI_API_KEY con la API KeyAPI Key de Model Studio.

macOS

Compruebe su shell predeterminada:

echo $SHELL

Establezca la variable de entorno según su tipo de shell:

Zsh

# Replace YOUR_API_KEY with the Model Studio API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc

Bash

# Replace YOUR_API_KEY with the Model Studio API Key
echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bash_profile

Aplique el cambio:

Zsh

source ~/.zshrc

Bash

source ~/.bash_profile

Windows

CMD

Establezca la variable de entorno:

REM Replace YOUR_API_KEY with the Model Studio API Key
setx OPENAI_API_KEY "YOUR_API_KEY"

Abra una nueva ventana de CMD para verificar:

echo %OPENAI_API_KEY%

PowerShell

Establezca la variable de entorno:

# Replace YOUR_API_KEY with the Model Studio API Key
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "YOUR_API_KEY", [EnvironmentVariableTarget]::User)

Abra una nueva ventana de PowerShell para verificar:

echo $env:OPENAI_API_KEY

Paso 2: Elegir un método de acceso

Elija un método de acceso según la API compatible con el modelo:

API Responses

Para modelos que admiten la API OpenAI Responses (como qwen3.7-max), compatible con la última versión de Codex.

model_provider = "Model_Studio"
model = "qwen3.7-max"
[model_providers.Model_Studio]
name = "Model_Studio"
base_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Luego configure los metadatos del modelo para cambiar entre modelos. Cree ~/.codex/model-catalog.local.json con los modelos admitidos por este plan:

{
  "models": [
    {
      "slug": "qwen3.8-max",
      "display_name": "qwen3.8-max",
      "description": "DashScope model: qwen3.8-max",
      "default_reasoning_level": "xhigh",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 983616,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 1,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "qwen3.7-max",
      "display_name": "qwen3.7-max",
      "description": "DashScope model: qwen3.7-max",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 2,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "deepseek-v4-pro",
      "display_name": "deepseek-v4-pro",
      "description": "DashScope model: deepseek-v4-pro",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 163840,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 3,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    },
    {
      "slug": "glm-5.2",
      "display_name": "glm-5.2",
      "description": "DashScope model: glm-5.2",
      "default_reasoning_level": "medium",
      "supported_reasoning_levels": [
        {
          "effort": "low",
          "description": "Fast responses with lighter reasoning"
        },
        {
          "effort": "medium",
          "description": "Balances speed and reasoning depth"
        },
        {
          "effort": "high",
          "description": "Greater reasoning depth for complex problems"
        },
        {
          "effort": "xhigh",
          "description": "Extra high reasoning depth for complex problems"
        }
      ],
      "context_window": 1000000,
      "effective_context_window_percent": 95,
      "supports_parallel_tool_calls": false,
      "supports_image_detail_original": false,
      "input_modalities": [
        "text"
      ],
      "shell_type": "default",
      "visibility": "list",
      "supported_in_api": true,
      "priority": 4,
      "base_instructions": "",
      "support_verbosity": false,
      "supports_reasoning_summaries": false,
      "experimental_supported_tools": [],
      "truncation_policy": {
        "mode": "bytes",
        "limit": 10000
      }
    }
  ]
}

Añada lo siguiente a ~/.codex/config.toml para apuntar al archivo:

model_catalog_json = "~/.codex/model-catalog.local.json"

Después de configurar, cambie entre modelos con codex -m (por ejemplo, codex -m qwen3.8-max), o ingrese /model en la TUI.

API Chat/Completions

Para modelos que solo admiten la API Chat/Completions. Instale Codex 0.80.0:

model_provider = "Model_Studio"
model = "qwen3.6-plus"
[model_providers.Model_Studio]
name = "Model_Studio"
base_url = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

Verificación de la configuración

Abra una nueva terminal e inicie Codex:

codex

Si se inicia la interfaz de chat, la configuración es correcta.

FAQ

¿Qué debo hacer si una herramienta de terceros reporta "domestic models not supported" o "check rejected / Bad request (400)"?

Causa: Algunas herramientas de gestión de terceros (como CC-Switch) envían una solicitud de sondeo de "comprobación de estado / prueba de conexión" al cambiar de proveedor. El formato de este sondeo difiere del formato de solicitud que utiliza realmente Codex, por lo que la puerta de enlace de Model Studio puede rechazarlo con 400 Bad request, y la herramienta entonces reporta "domestic models not supported". Este mensaje solo indica que el sondeo de comprobación de estado falló; no significa que Model Studio carezca de soporte para modelos nacionales, ni afecta el uso real de Codex.

Nota: Model Studio admite el uso de modelos de China continental a través de Codex. Para obtener detalles sobre la configuración, consulte Configurar credenciales de acceso arriba.

Solución: Configure Codex directamente en ~/.codex/config.toml como se describe en Configurar credenciales de acceso, sin depender del resultado de la comprobación de estado de la herramienta de terceros. Después de la configuración, inicie Codex como se describe en Verificar configuración; si la interfaz de chat se inicia normalmente, los modelos nacionales están funcionando.

¿Qué debo hacer si obtengo un error de configuración de wire_api?

Causa: Las versiones más recientes de Codex ya no admiten wire_api = "chat". Dependiendo de la versión, puede ver uno de los siguientes errores:

wire_api = "chat" is no longer supported
unknown configuration field wire_api

Solución:

Error wire_api = "chat" is no longer supported: Cambie wire_api a responses y verifique que base_url sea correcto. Consulte Configurar credenciales de acceso para ejemplos de configuración.
Error unknown configuration field wire_api: Elimine la línea wire_api de la sección del proveedor correspondiente en ~/.codex/config.toml.

¿Qué debo hacer si obtengo el error unexpected status 401 Unauthorized?

Causa:

Discrepancia de API Key (las claves de Token Plan, Coding Plan y Pago por uso no son intercambiables)
Suscripción caducada
API Key copiada incorrectamente (incompleta, contiene espacios o tiene un error tipográfico)

Solución:

Confirme que está utilizando la API Key correcta para su plan.
Revise la página de gestión de su plan para verificar la caducidad de la suscripción.
Vuelva a copiar la API Key sin espacios adicionales.
Si el error persiste, restablezca la API Key en la página de gestión de su plan y vuelva a configurar con la nueva clave.

¿Qué debo hacer si obtengo el error unexpected status 404 Not Found?

Causa: El valor de base_url o wire_api en el archivo de configuración es incorrecto.

Solución: Asegúrese de que base_url y wire_api coincidan con la configuración de su plan en Configurar credenciales de acceso arriba.

¿Qué debo hacer si obtengo el error "stream disconnected before completion: stream closed before response.completed"?

Causa: La conexión de streaming entre Codex y el servidor se interrumpió antes de que se completara la respuesta. Esto ocurre comúnmente en los siguientes escenarios:

El hilo de conversación es demasiado largo, lo que provoca que falle una solicitud de compactación de contexto
Red inestable que provoca que la conexión SSE o WebSocket se interrumpa a mitad de la transmisión
Sobrecarga del servidor o limitación de tasa que termina la conexión prematuramente

Solución:

Inicie un nuevo hilo de conversación para evitar la acumulación excesiva de contexto en un solo hilo.
Compruebe su conexión de red. Intente deshabilitar la VPN o el proxy y vuelva a intentarlo.
Espere y reintente. Codex cuenta con un mecanismo de reintento integrado que resuelve automáticamente la mayoría de los fallos transitorios.

Instalar Codex

Configuración de credenciales de acceso

Token Plan Personal Edition

Paso 1: Configurar variables de entorno

macOS

Zsh

Bash

Zsh

Bash

Windows

CMD

PowerShell

Paso 2: Elegir un método de acceso

API Responses

API Chat/Completions (otros modelos)

Token Plan Team Edition

Paso 1: Configurar variables de entorno

macOS

Zsh

Bash

Zsh

Bash

Windows

CMD

PowerShell

Paso 2: Elegir un método de acceso

API Responses

API Chat/Completions (otros modelos)

Plan de codificación

Paso 1: Configurar variables de entorno

macOS

Zsh

Bash

Zsh

Bash

Windows

CMD

PowerShell

Paso 2: Configurar acceso

API Chat/Completions

Pago por uso

Paso 1: Configurar variables de entorno

macOS

Zsh

Bash

Zsh

Bash

Windows

CMD

PowerShell

Paso 2: Elegir un método de acceso

API Responses

API Chat/Completions

Verificación de la configuración

FAQ

¿Qué debo hacer si una herramienta de terceros reporta "domestic models not supported" o "check rejected / Bad request (400)"?

¿Qué debo hacer si obtengo un error de configuración de wire_api?

¿Qué debo hacer si obtengo el error unexpected status 401 Unauthorized?

¿Qué debo hacer si obtengo el error unexpected status 404 Not Found?

¿Qué debo hacer si obtengo el error "stream disconnected before completion: stream closed before response.completed"?