Tradução de apoio para consulta. Código e identificadores técnicos preservados. Consultar referência original ↗

Codex

Assistente de codificação de IA de terminal da OpenAI

Conecte o Codex ao QwenCloud via Token Plan (Personal Edition), Token Plan (Team Edition) ou faturamento pré-pago.

Instale o Codex

Instale ou atualize Node.js (v18.0 ou posterior).
Execute o seguinte comando em um terminal para instalar o Codex.

npm install -g @openai/codex

Execute o seguinte comando para verificar a instalação.

codex --version

Configurar credenciais de acesso

Para conectar, edite o arquivo de configuração ~/.codex/config.toml e configure a variável de ambiente OPENAI_API_KEY. Substitua os valores correspondentes com base no plano de faturamento selecionado.

Plano de token (edição pessoal)

Para model, selecione um modelo compatível. Defina o OPENAI_API_KEY variável de ambiente para o Token Plan (Personal Edition) dedicado API Key.

Etapa 1: configurar variáveis de ambiente

Defina o OPENAI_API_KEY variável de ambiente para a chave de API dedicada do Token Plan (Personal Edition).

macOS

1. Execute o seguinte comando em um terminal para verificar o tipo de shell padrão.

```bash
echo $SHELL
```

2. Defina a variável de ambiente com base no seu tipo de shell:

Zsh

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

Bash

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




3. Execute o seguinte comando para aplicar a variável de ambiente.

Zsh

    ```bash
    source ~/.zshrc
    ```

Bash

    ```bash
    source ~/.bash_profile
    ```

Windows

CMD

    1. Execute o seguinte comando no CMD para definir a variável de ambiente.

    ```powershell
    REM Replace YOUR_API_KEY with the Token Plan (Personal Edition) API Key
    setx OPENAI_API_KEY "YOUR_API_KEY"
    ```

    2. Abra uma nova janela CMD e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo %OPENAI_API_KEY%
    ```

PowerShell

    1. Execute o seguinte comando no PowerShell para definir a variável de ambiente.

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

    2. Abra uma nova janela do PowerShell e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo $env:OPENAI_API_KEY
    ```

Passo 2: Escolha um método de acesso

Escolha um método de acesso com base na API compatível com o modelo:

API de respostas

Se o modelo selecionado for compatível com a API OpenAI Responses, você pode usar a versão mais recente do 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.maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Em seguida, configure os metadados do modelo para poder alternar entre modelos. Criar ~/.codex/model-catalog.local.json com os modelos suportados por este plano:

{
  "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-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
      }
    }
  ]
}

Adicione o seguinte a ~/.codex/config.toml para apontar para o arquivo:

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

Após a configuração, alterne entre os modelos com codex -m (por exemplo, codex -m qwen3.8-flash) ou digite /model na TUI.

API de bate-papo/conclusões (outros modelos)

Outros modelos exigem a API Chat/Completions. Instale uma versão mais antiga do Codex, como 0.80.0 (as versões mais recentes do Codex não suportam mais wire_api = "chat"; se você receber um erro após a atualização, consulte as perguntas frequentes abaixo):

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.maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

**qwen3.8-max modo de pensamento **:

pensando: Suporta habilitado e desabilitado (modo de pensamento híbrido).
temperatura: o padrão é 0,6 no modo de pensamento. Valores abaixo de 0,6 são ajustados automaticamente para 0,6.
reasoning_effort: Controla a profundidade do raciocínio. Opções: xalto, médio, baixo. Padrão: xalto.

Plano de Token (Edição de Equipe)

Para model, selecione um modelo compatível. Defina o OPENAI_API_KEY variável de ambiente para o Token Plan (Team Edition) dedicado API Key.

Etapa 1: configurar variáveis de ambiente

Defina o OPENAI_API_KEY variável de ambiente para a chave de API dedicada do Token Plan (Team Edition).

macOS

1. Execute o seguinte comando em um terminal para verificar o tipo de shell padrão.

```bash
echo $SHELL
```

2. Defina a variável de ambiente com base no seu tipo de shell:

Zsh

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

Bash

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




3. Execute o seguinte comando para aplicar a variável de ambiente.

Zsh

    ```bash
    source ~/.zshrc
    ```

Bash

    ```bash
    source ~/.bash_profile
    ```

Windows

CMD

    1. Execute o seguinte comando no CMD para definir a variável de ambiente.

    ```powershell
    REM Replace YOUR_API_KEY with the Token Plan (Team Edition) API Key
    setx OPENAI_API_KEY "YOUR_API_KEY"
    ```

    2. Abra uma nova janela CMD e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo %OPENAI_API_KEY%
    ```

PowerShell

    1. Execute o seguinte comando no PowerShell para definir a variável de ambiente.

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

    2. Abra uma nova janela do PowerShell e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo $env:OPENAI_API_KEY
    ```

Passo 2: Escolha um método de acesso

Escolha um método de acesso com base na API compatível com o modelo:

API de respostas

Se o modelo selecionado for compatível com a API OpenAI Responses, você pode usar a versão mais recente do 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.maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Em seguida, configure os metadados do modelo para poder alternar entre modelos. Criar ~/.codex/model-catalog.local.json com os modelos suportados por este plano:

{
  "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-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
      }
    }
  ]
}

Adicione o seguinte a ~/.codex/config.toml para apontar para o arquivo:

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

Após a configuração, alterne entre os modelos com codex -m (por exemplo, codex -m qwen3.8-flash) ou digite /model na TUI.

API de bate-papo/conclusões (outros modelos)

npm install -g @openai/codex@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.maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

**qwen3.8-max modo de pensamento **:

pensando: Suporta habilitado e desabilitado (modo de pensamento híbrido).
temperatura: o padrão é 0,6 no modo de pensamento. Valores abaixo de 0,6 são ajustados automaticamente para 0,6.
reasoning_effort: Controla a profundidade do raciocínio. Opções: xalto, médio, baixo. Padrão: xalto.

Pague conforme o uso

Defina o OPENAI_API_KEY variável de ambiente para o seu QwenCloud Chave API e escolha entre modelos suportados.

Definir base_url para https://maas.qwencloudapi.com/compatible-mode/v1.

O pagamento conforme o uso oferece suporte à API de respostas e à API de bate-papo/conclusões. Escolha com base no modelo que você está usando:

Etapa 1: configurar variáveis de ambiente

Defina o OPENAI_API_KEY variável de ambiente para o seu QwenCloud Chave API.

macOS

1. Execute o seguinte comando em um terminal para verificar o tipo de shell padrão.

```bash
echo $SHELL
```

2. Defina a variável de ambiente com base no seu tipo de shell:

Zsh

    ```bash
    # Replace YOUR_API_KEY with the QwenCloud API Key
    echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.zshrc
    ```

Bash

    ```bash
    # Replace YOUR_API_KEY with the QwenCloud API Key
    echo 'export OPENAI_API_KEY="YOUR_API_KEY"' >> ~/.bash_profile
    ```
  




3. Execute o seguinte comando para aplicar a variável de ambiente.

Zsh

    ```bash
    source ~/.zshrc
    ```

Bash

    ```bash
    source ~/.bash_profile
    ```

Windows

CMD

    1. Execute o seguinte comando no CMD para definir a variável de ambiente.

    ```powershell
    REM Replace YOUR_API_KEY with the QwenCloud API Key
    setx OPENAI_API_KEY "YOUR_API_KEY"
    ```

    2. Abra uma nova janela CMD e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo %OPENAI_API_KEY%
    ```

PowerShell

    1. Execute o seguinte comando no PowerShell para definir a variável de ambiente.

    ```powershell
    # Replace YOUR_API_KEY with the QwenCloud API Key
    [Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "YOUR_API_KEY", [EnvironmentVariableTarget]::User)
    ```

    2. Abra uma nova janela do PowerShell e execute o seguinte comando para verificar se a variável de ambiente está definida.

    ```powershell
    echo $env:OPENAI_API_KEY
    ```

Passo 2: Escolha um método de acesso

Escolha um método de acesso com base na API compatível com o modelo:

API de respostas

Aplicável a modelos que suportam a API OpenAI Responses (como qwen3.7-max), compatível com a versão mais recente do Codex.

model_provider = "Model_Studio"
model = "qwen3.7-max"
[model_providers.Model_Studio]
name = "Model_Studio"
base_url = "https://maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"

Em seguida, configure os metadados do modelo para poder alternar entre modelos. Criar ~/.codex/model-catalog.local.json com os modelos suportados por este plano:

{
  "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
      }
    }
  ]
}

Adicione o seguinte a ~/.codex/config.toml para apontar para o arquivo:

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

Após a configuração, alterne entre os modelos com codex -m (por exemplo, codex -m qwen3.8-max) ou digite /model na TUI.

API de bate-papo/conclusões

Aplicável a modelos que suportam apenas a API Chat/Completions. Requer a instalação do Codex 0.80.0:

npm install -g @openai/codex@0.80.0

model_provider = "Model_Studio"
model = "qwen3.6-plus"
[model_providers.Model_Studio]
name = "Model_Studio"
base_url = "https://maas.qwencloudapi.com/compatible-mode/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

Verifique a configuração

Após a conclusão da configuração, abra uma nova janela de terminal e execute o seguinte comando para iniciar o Codex:

codex

Se a interface de chat for iniciada com sucesso, a configuração está correta.

Perguntas frequentes

O que devo fazer se uma ferramenta de terceiros relatar "modelos domésticos não suportados" ou "verificação rejeitada/solicitação incorreta (400)"?

Causa: algumas ferramentas de gerenciamento de terceiros (como CC-Switch) enviam uma solicitação de sondagem de "verificação de integridade/teste de conexão" ao trocar de provedor. O formato desta investigação difere do formato de solicitação que o Codex realmente usa, então o QwenCloud o gateway pode rejeitá-lo com 400 Solicitação incorreta e a ferramenta relata "modelos domésticos não suportados". Esta mensagem indica apenas que a investigação de verificação de integridade falhou; isso não significa QwenCloud não tem suporte para modelos domésticos, nem afeta o uso real do Codex.

Nota: QwenCloud apoia o uso de modelos domésticos, como qwen3.7-max, qwen3.7-plus, qwen3.6-plus, qwen3.6-flashe glm-5 através do Codex. Para obter detalhes de configuração, consulte Configurar credenciais de acesso acima.

Solução: Configure o Codex diretamente no ~/.codex/config.toml conforme descrito em Configurar credenciais de acesso, sem depender do resultado da verificação de integridade da ferramenta de terceiros. Após a configuração, inicie o Codex conforme descrito em Verificar configuração; se a interface de chat iniciar normalmente, os modelos domésticos estão funcionando.

O que devo fazer se receber um erro de configuração wire_api?

Causa: versões mais recentes do Codex não são mais compatíveis wire_api = "chat". Dependendo da versão, você poderá ver um dos seguintes erros:

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

Solução:

Erro wire_api = "chat" is no longer supported: Alterar wire_api para responses e verifique isso base_url está correto. Consulte Configurar credenciais de acesso para exemplos de configuração.
Erro unknown configuration field wire_api: Remova o wire_api linha da seção do provedor correspondente em ~/.codex/config.toml.

O que devo fazer se receber o erro "status inesperado 401 Não autorizado"?

Causa:

Usar uma chave de API de um plano diferente (chaves de API para plano de token (edição pessoal), plano de token (edição de equipe) e pagamento conforme o uso não são intercambiáveis)
A assinatura expirou
A chave de API foi copiada de forma incompleta, contém espaços ou contém um erro de digitação

Solução:

Verifique se você está usando a chave de API dedicada para o plano selecionado.
Acesse a página de gerenciamento do plano selecionado e verifique se a assinatura expirou.
Copie novamente a chave API e certifique-se de que esteja completa e sem espaços.
Se o erro persistir após a verificação acima, redefina a Chave API na página de gerenciamento do plano selecionado. Após a redefinição, use a nova chave API para configuração.

O que devo fazer se receber o erro "status inesperado 404 não encontrado"?

Causa: O base_url ou wire_api no arquivo de configuração está incorreto.

Solução: verifique se base_url e wire_api corresponda à configuração do plano selecionado. Veja os exemplos de configuração do seu plano em Configurar credenciais de acesso acima.

O que devo fazer se receber o erro "stream desconectado antes da conclusão: stream fechado antes da resposta.completed"?

Causa: A conexão de streaming entre o Codex e o servidor foi interrompida antes da resposta ser concluída. Isso geralmente ocorre nos seguintes cenários:

O thread de conversação é muito longo, causando falha na solicitação de compactação de contexto
Rede instável fazendo com que a conexão SSE ou WebSocket caia no meio do fluxo
Sobrecarga do servidor ou limitação de taxa que encerra a conexão antecipadamente

Solução:

Inicie um novo tópico de conversa para evitar acúmulo excessivo de contexto em um único tópico.
Verifique sua conexão de rede. Tente desativar a VPN ou proxy e tente novamente.
Espere e tente novamente. O Codex possui um mecanismo de nova tentativa integrado que resolve automaticamente a maioria das falhas transitórias.

O que devo fazer se receber um erro 429 por limitação de taxa ou esgotamento de cota?

Causa: Um erro 429 ocorre em duas situações:

Limite de taxa excedido (429 Requests rate limit exceeded): as solicitações são muito frequentes em um curto período.
Cota esgotada (429 Allocated quota exceeded ou Your token-plan 1-week quota has been exhausted): O limite semanal ou mensal do Token Plan foi atingido.

Solução:

Limite de taxa excedido: aguarde um minuto e tente novamente com uma frequência de solicitação reduzida.
Cota esgotada: Aguarde o término do período de janela correspondente (semanal ou mensal), após o qual a cota é zerada automaticamente; ou comprar um Pacote de Créditos (os Créditos do Pacote de Créditos não estão sujeitos a limites de janela); ou atualize seu plano. Observe que o tempo de reinicialização na mensagem de erro (por exemplo, The quota will reset at HH:MM:SS UTC) está no Tempo Universal Coordenado (UTC).