FAQ-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

What is the difference between Token Plan (Team Edition) and Coding Plan?

	Token Plan (Team Edition)	Coding Plan
Use cases	Day-to-day work for solo founders, teams, and enterprises	Individual development scenarios
Supported models	Text generation and image generation models	Text generation models
Billing method	Credits deducted based on token consumption	Billed per model call
Usage frequency	No per 5-hour / per week quota	Quota per 5 hours / per week
API Key and Base URL	Generate a dedicated API key in the management console. For the base URL, see Quick start	Get your dedicated API key and base URL from the Coding Plan page
Peak-time performance	Multi-tenant isolation	Requests may queue during peak hours
Data security	Your data is not used to train models	User data authorization required

Connection and usage

How do I use image generation models in coding tools?

Image generation models use separate APIs and cannot be called directly through the text model's Base URL. Integrate them through your tool's Skill or extension mechanism. For configuration details, see the image generation model integration section in the integration guide for each tool.

Common errors and solutions

Error message	Possible cause	Solution
401 InvalidApiKey: No API-key provided.	The request did not include the API key in either the `Authorization: Bearer` or `x-api-key` header.	Generate an API key in the management console and configure it in your tool.
401 InvalidApiKey: Invalid API-key provided.	You mistakenly used the Model Studio general-purpose API key (sk-xxx format) or the Coding Plan API key. The Token Plan (Team Edition) subscription has expired. The API key was copied incompletely or contains spaces.	Confirm you are using the Token Plan dedicated API key. Ensure the key is copied completely without any spaces. Verify whether the subscription has expired. If the error persists, reset the API key, then configure the new key.
404 model 'xxx' not found or not supported 400 Model not exist.	The model name is misspelled or has incorrect capitalization. The model ID is not in the plan's supported list.	Model names are case-sensitive. Use a model ID supported by your plan. Verify that the selected plan includes the model.
401 invalid access token or token expired	You mistakenly used the Base URL for Coding Plan or another plan.	Anthropic-compatible: `https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic` OpenAI-compatible: `https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1`
401 Incorrect API key provided	You mistakenly used the Model Studio general-purpose Base URL (dashscope.aliyuncs.com).	Anthropic-compatible: `https://token-plan.cn-beijing.maas.aliyuncs.com/apps/anthropic` OpenAI-compatible: `https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1`
400 InvalidParameter: Range of input length should be [1, xxx]	The input content (including conversation history and code context) exceeds the model's maximum context length.	Start a new session to clear history, or use the tool's built-in context compression command (such as `/compact` in Claude Code or `/clear` in Qwen Code). You can also switch to a model with a larger context window.
400 InvalidParameter: url error, please check url！	The Base URL path does not match the protocol. For example, the OpenAI-compatible path is configured on the Anthropic endpoint, or vice versa.	Choose the endpoint matching the protocol your tool uses: Anthropic-compatible (Claude Code and similar): ends with `/apps/anthropic`. OpenAI-compatible (Cursor, Qwen Code, and similar): ends with `/compatible-mode/v1`.
400 InvalidParameter: Range of max_tokens should be [1, xxxx]	The `max_tokens` value in the request (or the maximum output length in the tool configuration) exceeds the maximum output tokens supported by the current model.	Set `max_tokens` to a value not exceeding the limit shown in the error message.
400 invalid_parameter_error: The thinking_budget parameter must be a positive integer and not greater than xxxxx	The thinking length configured in the tool (such as `thinking_budget` or `budgetTokens`) exceeds the limit supported by the current model. The limit differs by model — use the value shown in the error.	Set the thinking length to a value not exceeding the limit shown in the error, or remove the parameter for models that do not support thinking mode.
400 data_inspection_failed: Input text data may contain inappropriate content.	The input or output triggered the platform's content safety policy.	Modify the input and resubmit. If the issue recurs, adjust the prompt to avoid sensitive topics.
429 API-Key Requests rate limit exceeded, please try again later.	Requests were too dense within a short period and triggered the model rate limit.	Wait one minute and retry. If this occurs frequently, reduce the request frequency and verify the API key is not being shared with others.
429 Throttling.AllocationQuota: Allocated quota exceeded, please increase your quota limit. insufficient_quota: You exceeded your current quota, please check your plan and billing details.	This error can be triggered by either of two causes: Plan quota depleted: both the seat quota and the shared quota pack are exhausted. Model rate limit triggered: even when the plan quota is sufficient, this error occurs when the tokens consumed per second or per minute (TPS/TPM) exceed the model's rate limit threshold. Rate limits are calculated at the Alibaba Cloud account level — the combined usage of all RAM users, workspaces, and API keys under the account counts together. Even if the per-minute total stays within the limit, a short burst of requests can still trigger it.	Quota depleted: purchase additional seats (after purchasing, assign the new seat to a member before use), purchase a shared quota pack, or wait for the quota to reset automatically at the next billing cycle. Rate limit triggered: wait about one minute and retry, and smooth your request rate (for example, use even scheduling, exponential backoff, or a request queue) to avoid instantaneous spikes. If the default rate limit does not meet your needs, increase the model's temporary TPM quota on the Increase Rate Limits page in the Model Studio console. For more about rate limits and how to avoid them, see Rate limiting.
Connection error	The Base URL domain is misspelled, or a network connection issue occurred.	Check the Base URL domain spelling and your network connection.

Product features

Can the Token Plan (Team Edition) API key be used with other plans or general-purpose APIs?

No. The API keys and base URLs for Token Plan (Team Edition), Coding Plan, and the Model Studio pay-as-you-go service are not interchangeable. Using an API key from another plan will not deduct from your Token Plan (Team Edition) quota.

Can I use one subscription across multiple tools?

Yes. You can use the same API key across all compatible AI tools, and all usage is deducted from the same shared quota. Each member holds an independent API key that must not be shared with other members.

What are the usage restrictions?

This plan is for interactive use within compatible AI coding and agent tools only. It cannot be used for automated scripts or application backends. Violations may result in subscription suspension or API key revocation.

Where do I access team management?

Alibaba Cloud accounts and RAM users can sign in to the Token Plan console, then on the My Subscriptions page, click Settings in the Team Edition card to edit organization information, and click Assign seats in the Subscription details area to manage members. Members who joined via SSO or DingTalk sign in to the management platform through the address shared by the administrator. For details, see Access.

How do members obtain an API key?

The administrator creates a member account in the management platform, assigns a seat, and then generates an API key for the member. Members cannot generate API keys on their own and must contact the administrator. For details, see Team management.

Purchasing

Can I purchase multiple plans at the same time?

Each Alibaba Cloud account can have only one active subscription. Within the same subscription, you can purchase multiple seats of each type. Shared quota packs can also be stacked.

Can I cancel my subscription?

Yes, by seat. On the My Subscriptions page in the console, click Cancel next to the seat. Seats with usage cannot be canceled. Refunds are returned to the original payment account within 1 to 3 business days. For details, see Subscription management.

Does an overdue Alibaba Cloud account affect Token Plan (Team Edition)?

Token Plan (Team Edition) is a prepaid subscription. As long as your quota is not exhausted and the subscription has not expired, an overdue Alibaba Cloud account does not affect your usage.

Billing and metering

What are the Credit deduction rules?

Credits consumed per request depend on the input tokens, cached tokens, and output tokens. Credits are first deducted from the seat quota, then from the shared quota pack. When all quotas are depleted, the service is suspended until the next billing cycle or until you purchase a shared quota pack.

How do I check my usage?

View usage details for your plan and shared quota pack on the Token Plan (Team Edition) page. Administrators can also view detailed consumption records for all members on the Usage Analysis page of the management platform. For details, see Team management.

How does usage reset work?

The seat quota resets when each subscription month expires. Unused quota does not carry over to the next month. The shared quota pack quota also resets monthly.

What happens when I exceed my quota?

After the seat quota is exhausted, Credits are automatically deducted from the shared quota pack. When all quotas are depleted, the service is suspended. To restore service:

Purchase a shared quota pack.
Wait for the quota to reset automatically at the next billing cycle.

Why didn't my Credits increase after renewal?

Token Plan (Team Edition) seat quotas reset automatically at the end of each subscription month. Renewal only extends the subscription period and does not immediately add Credits to the current month. If your current month's quota is exhausted, you can:

Purchase a shared quota pack.
Upgrade to a higher-tier seat.
Wait for the quota to reset at the next billing cycle.

Data security

How is data security ensured?

Token Plan (Team Edition) does not use conversation data to train models. Data is encrypted in transit using HTTPS and isolated through a multi-tenant architecture to provide enterprise-grade data isolation.