Claude Code - QwenCloud

When using qwen4-max-preview, set CLAUDE_CODE_MAX_OUTPUT_TOKENS=64000 if long output is truncated.

Add a model

Choose your client and complete the configuration.

CLI
CC Switch
IDE plugin
Desktop

Configure the model

Token Plan
Pay-as-you-go

Replace YOUR_API_KEY with your Token Plan API Key.

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://token-plan.maas.qwencloudapi.com/apps/anthropic"
export ANTHROPIC_MODEL="auto"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="qwen3.6-flash"
export ANTHROPIC_DEFAULT_SONNET_MODEL="qwen3.8-flash"
export ANTHROPIC_DEFAULT_OPUS_MODEL="qwen4-max-preview"
export CLAUDE_CODE_SUBAGENT_MODEL="auto"
export CLAUDE_CODE_MAX_CONTEXT_TOKENS="983616"

Replace YOUR_API_KEY with your QwenCloud API Key.

export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
# Singapore (ap-southeast-1). For another region, replace ap-southeast-1 in the URL.
# API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
export ANTHROPIC_BASE_URL="https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic"
export ANTHROPIC_MODEL="qwen3.7-max"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="qwen3.6-flash"
export ANTHROPIC_DEFAULT_SONNET_MODEL="qwen3.7-max"
export ANTHROPIC_DEFAULT_OPUS_MODEL="qwen3.7-max"
export CLAUDE_CODE_SUBAGENT_MODEL="qwen3.7-max"

These environment variables apply only to the current terminal. For persistent configuration, use Configure with a configuration file.

Verify

Run the following command to verify:

claude -p "Hello"

Install CC Switch

Download and install CC Switch.

Add a QwenCloud provider

In CC Switch, select the Claude Code icon, click +, and fill in the fields in the corresponding tab.

Token Plan
Pay-as-you-go

Provider name: QwenCloud-Token Plan
API Key: get from console
Endpoint: https://token-plan.maas.qwencloudapi.com/apps/anthropic

Configure model mapping

Expand Advanced Options and set the main, Haiku, Sonnet, and Opus models. Example:

Main model: qwen3.8-max
Haiku default model: qwen3.8-flash
Sonnet default model: qwen3.8-flash
Opus default model: qwen3.8-max

Switch to the Claude Desktop panel

In CC Switch, switch to the Claude Desktop panel on the left. If it is not shown, enable it in Settings > General > App visibility.

Import the provider

Import the provider already configured in Claude Code, or click + to add one. Turn on Needs model mapping for QwenCloud model IDs and map Sonnet, Opus, and Haiku to the actual models.

Enable local routing

Go to Settings > Routing > Local Routing and turn on the main-page switch; in the Claude Desktop panel, turn on local routing. The default address is 127.0.0.1:15721.

Enable and restart the desktop app

Click Enable on the provider card and do not enter an API Key manually in the desktop app. Keep CC Switch running, then fully quit and restart the desktop app.

Configure with a Configuration File

In addition to the options above, you can also connect using a configuration file.

Open or create the configuration file

macOS / Linux: ~/.claude/settings.json
Windows: C:\Users\<username>\.claude\settings.json

Add the configuration

Token Plan
Pay-as-you-go

Replace YOUR_API_KEY with your Token Plan API Key.

{
    "env": {
        "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
        "ANTHROPIC_BASE_URL": "https://token-plan.maas.qwencloudapi.com/apps/anthropic",
        "ANTHROPIC_MODEL": "auto",
        "ANTHROPIC_DEFAULT_HAIKU_MODEL": "qwen3.6-flash",
        "ANTHROPIC_DEFAULT_SONNET_MODEL": "qwen3.8-flash",
        "ANTHROPIC_DEFAULT_OPUS_MODEL": "qwen4-max-preview",
        "CLAUDE_CODE_SUBAGENT_MODEL": "auto",
        "CLAUDE_CODE_MAX_CONTEXT_TOKENS": "983616"
    }
}

Replace YOUR_API_KEY with your QwenCloud API Key. The example uses the Singapore (ap-southeast-1) region; for another region, replace ap-southeast-1 in the URL. API keys are region-specific; see Regions and endpoints.

{
    "env": {
        "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
        "ANTHROPIC_BASE_URL": "https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic",
        "ANTHROPIC_MODEL": "qwen3.7-max",
        "ANTHROPIC_DEFAULT_HAIKU_MODEL": "qwen3.6-flash",
        "ANTHROPIC_DEFAULT_SONNET_MODEL": "qwen3.7-max",
        "ANTHROPIC_DEFAULT_OPUS_MODEL": "qwen3.7-max",
        "CLAUDE_CODE_SUBAGENT_MODEL": "qwen3.7-max"
    }
}

Verify

After saving, run the following command to verify:

claude -p "Hello"

Configure Context Window Size

Claude Code defaults to a 200K context window. If the model supports 1M, extend it to 1M (1,000,000 tokens). Method 1: Set via environment variable Add CLAUDE_CODE_MAX_CONTEXT_TOKENS to the env field in ~/.claude/settings.json. The example uses the Singapore (ap-southeast-1) region; API keys are region-specific, see Regions and endpoints.

{
    "env": {
        "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
        "ANTHROPIC_BASE_URL": "https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic",
        "ANTHROPIC_MODEL": "qwen3.7-plus",
        "CLAUDE_CODE_MAX_CONTEXT_TOKENS": "1000000"
    }
}

Method 2: Use a model name suffix Append [1m] to the model name. This works with QwenCloud models that support a 1M context window. The example uses the Singapore (ap-southeast-1) region; see Regions and endpoints.

{
    "env": {
        "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
        "ANTHROPIC_BASE_URL": "https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic",
        "ANTHROPIC_MODEL": "qwen3.7-plus[1m]",
        "ANTHROPIC_DEFAULT_SONNET_MODEL": "qwen3.7-plus[1m]",
        "ANTHROPIC_DEFAULT_OPUS_MODEL": "qwen3.7-plus[1m]",
        "CLAUDE_CODE_SUBAGENT_MODEL": "qwen3.7-plus[1m]"
    }
}

After modifying the configuration, open a new terminal window to restart Claude Code for the changes to take effect.

Permission modes

Claude Code provides six permission modes:

default: Prompts for confirmation before every operation.
acceptEdits: Approves file edits automatically. Other operations still prompt for confirmation.
plan: Read-only planning mode. No changes are executed.
dontAsk: Does not prompt. An operation that would require a prompt is rejected directly.
bypassPermissions: Bypasses all permission checks.
delegate: Delegated mode.

Method 1: Command-line flag Use --permission-mode to set the default permission mode for a session:

claude --permission-mode plan
claude --permission-mode acceptEdits

Method 2: Interactive command Enter /permissions in a session to manage pre-approve and pre-deny rules for the bash, edit, and MCP tools. Method 3: settings.json configuration Configure the permissions field in ~/.claude/settings.json:

{
    "permissions": {
        "allow": ["Bash(git:*)", "Read", "Edit"],
        "deny": ["Bash(rm:*)"],
        "defaultMode": "default"
    }
}

Integrate the QwenCloud CLI

Install the QwenCloud CLI, then configure your API key and describe the task in natural language.

Install the CLI

Please install the QwenCloud CLI globally: npm install -g @qwencloud/qwencloud-cli

Configure the API Key

Go to API keys to get an API Key, then tell Claude Code:

My API Key is: sk-xxxxxxxxxxxxx

Get started

Describe your task in natural language, for example:

Generate 6 Amazon e-commerce hero images for a white wireless Bluetooth headset.
Generate a 30-second product demo video for a white wireless Bluetooth headset.

Error Codes

If you encounter errors during configuration, refer to the FAQ documentation for your billing plan:

Token Plan: Individual FAQ · Team Edition FAQ
Pay-as-you-go: Anthropic API compatible - Error codes

FAQ

Edit or create ~/.claude.json (Windows path: C:\Users\<username>\.claude.json), and set hasCompletedOnboarding to true to skip the official Anthropic login verification.

{
  "hasCompletedOnboarding": true
}

Requests return 401 invalid_api_key

The API key type does not match ANTHROPIC_BASE_URL. QwenCloud provides multiple access methods, and each access method uses a different base URL and a dedicated API key.

Access method	Base URL	API key
Token Plan	`https://token-plan.maas.qwencloudapi.com/apps/anthropic`	Token Plan API key
Pay-as-you-go	`https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic`	QwenCloud API key (starts with `sk-`)

Troubleshooting steps:

Check the request URL. Check ANTHROPIC_BASE_URL in ~/.claude/settings.json.
Confirm the API key type. Using the table above, confirm that your API key type matches the base URL.
Correct the configuration. When you use a QwenCloud Pay-as-you-go API key, set ANTHROPIC_BASE_URL to https://ap-southeast-1.maas.qwencloudapi.com/apps/anthropic.

After starting Claude Code, the interface displays "Unable to connect to Anthropic services. Failed to connect to api.anthropic.com: ERR_BAD_REQUEST"

Claude Code is connecting to the official Anthropic service instead of QwenCloud. This usually means the environment variables are missing or have not taken effect. Follow these steps:

Check the configuration. Run the /status command after starting Claude Code. Verify that ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN point to the QwenCloud address. If the output is empty or shows a non-QwenCloud address, check the settings.json configuration.
Verify hasCompletedOnboarding. Confirm that hasCompletedOnboarding is set to true in ~/.claude.json. Without this, Claude Code attempts to connect to the official Anthropic service for login verification on startup.
Open a new terminal. After editing the configuration file, open a new terminal window and run claude for the changes to take effect.
Update Claude Code. If the issue persists after all the steps above, the Claude Code version may be outdated. Run npm install -g @anthropic-ai/claude-code@latest to update to the latest version, then try again.

Model switching does not take effect when using the legacy interface

The legacy compatible interface https://ap-southeast-1.maas.qwencloudapi.com/api/v2/apps/claude-code-proxy only supports deprecated models. Specifying other models has no effect. To use available models, migrate to the new interface by following the configuration in this document.

CC Switch reports "No available model list endpoint found. Check the Base URL or confirm that the provider has opened the port" when adding a provider

This message comes from the connectivity check CC Switch runs when saving a provider: it probes a model list endpoint (such as /v1/models) against the configured request URL. QwenCloud's Anthropic-compatible endpoint (ending in /apps/anthropic) only provides the messages endpoint /v1/messages and does not provide a model list endpoint, so the probe returns 404 and CC Switch reports "No available model list endpoint found".This message does not affect normal use of Claude Code and can be ignored. Claude Code sends conversations through /v1/messages, and the models it uses are specified directly by the model mapping in CC Switch's Advanced options, without relying on auto-discovery from a model list endpoint. When the request URL and API Key are configured correctly, simply click Enable and start a new Claude Code session to chat normally.If you still cannot chat, verify that the request URL ends in /apps/anthropic without an extra /v1, and that you have filled in the models supported by your plan in the model mapping under Advanced options.

Model mapping in CC Switch returns AccessDenied

If model calls fail in Claude Code with an AccessDenied error (HTTP 403, code: access_denied) after you configure the model mapping, check whether the model is marked as Upcoming deprecation in QwenCloud console > Model Gallery. Models marked for upcoming deprecation still appear in the list, but API calls return 403 AccessDenied. Follow these steps:

Check whether the model is marked for deprecation. In QwenCloud console > Model Gallery, search for the model you are using and check its status label.
Switch to the latest available model. Replace the legacy model (such as qwen-coder-turbo-0919) in the model mapping with the latest available model (such as qwen3.8-max).
Reconfigure the model mapping and test. Update the model mapping under Advanced options in CC Switch, click Enable, and start a new Claude Code session to verify.

Pay attention to the model lifecycle. Models marked for upcoming deprecation in QwenCloud console > Model Gallery may become unavailable at any time. You can check a model's availability status there.

​Add a model

​Configure with a Configuration File

​Configure Context Window Size

​Permission modes

​Integrate the QwenCloud CLI

​Error Codes

​FAQ

Add a model

Configure with a Configuration File

Configure Context Window Size

Permission modes

Integrate the QwenCloud CLI

Error Codes

FAQ