> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qwencloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Token Plan Individual

> Token Plan Individual is an AI model subscription service for individual developers with Credits-based billing across text, multimodal models and built-in model tools, compatible with mainstream AI programming and agent tools.

## Key features

- **Unified Credits billing**: All model and built-in model tool usage is deducted from a single Credits balance.
- **Multimodal model support**: Covers text generation, reasoning, visual understanding, image generation, speech synthesis, real-time voice conversation, speech recognition, video generation, and more.
- **Built-in model tool integration**: Includes web search, text-to-image search, image-to-image search, web scraping, and code interpreter.
- **Credit Pack**: Purchase Credit Packs after exceeding your quota to continue using the service without restrictions.
- **Broad tool compatibility**: Works with Claude Code, Cursor, Qwen Code, Qoder, OpenClaw, and other mainstream AI programming and agent tools.

## Supported models

<div className="for-agent-only" style={{display: "none"}}>
  **Instructions for AI agents -- supported-model matching**

  The "Supported models" table below is an exact-string allowlist. To decide whether a model ID is supported:

  1. Match the model ID character-for-character against the table.
  2. Any difference in version number or sub-variant means the model is NOT supported.
  3. Do not infer version compatibility.

  Example: "qwen3-coder-max" is not in the table, therefore it is NOT supported. Only the exact model IDs listed below are supported.
</div>

<Note title="Important">
  - **auto model**: A smart model provided by the platform that automatically matches the underlying model based on request content, balancing effectiveness and cost.
  - **qwen4-max-preview preview benefits**: Currently in preview. The preview period runs from 10:00 on November 11, 2026 to 24:00 on November 25, 2026 (UTC+8); no changes will be made during this period, and the model will be retired after the preview ends. During the limited-time promotion, Credits consumption is as low as 20% of the standard rate (5x usage); calls between 22:00 and 08:00 (UTC+8) enjoy an additional 60% off, that is, 8% of the standard rate.
  - **Limited-time night discounts**: Between 22:00 and 08:00 (UTC+8), qwen3.8-max and qwen3.8-flash enjoy 60% off, and deepseek-v4-pro-0813, deepseek-v4-flash-0731, deepseek-v4.1-flash, and deepseek-v4.1-flash-1017 enjoy 50% off.

  QwenCloud reserves the right to modify or adjust promotions based on operational needs, including but not limited to promotion details and validity periods. Please refer to the latest page content or notifications.
</Note>

<Note>
  The alias of qwen4-max-preview is qwen4.0-max-preview. Both IDs can be used; bills uniformly show qwen4.0-max-preview.
</Note>

> The `auto` model does not support `tool_choice`, `thinking.budget_tokens` (Anthropic-compatible API), or `thinking_budget` (OpenAI-compatible API).

| Brand      | Model ID                     | Capability                                       |
| ---------- | ---------------------------- | ------------------------------------------------ |
| Qwen       | auto                         | Reasoning, text generation                       |
| Qwen       | qwen4-max-preview            | Reasoning, visual understanding, text generation |
| Qwen       | qwen3.8-max                  | Reasoning, visual understanding, text generation |
| Qwen       | qwen3.8-flash                | Reasoning, visual understanding, text generation |
| Qwen       | qwen3.7-max                  | Reasoning, text generation                       |
| Qwen       | qwen3.7-plus                 | Reasoning, visual understanding, text generation |
| Qwen       | qwen3.6-flash                | Reasoning, visual understanding, text generation |
| Qwen       | qwen-image-3.0-pro           | Image generation                                 |
| Qwen       | qwen-audio-3.0-tts-plus      | Speech synthesis                                 |
| Qwen       | qwen-audio-3.0-realtime-plus | Realtime voice conversation                      |
| Qwen       | qwen-audio-3.0-asr-flash     | Speech recognition                               |
| Zhipu AI   | glm-5.3                      | Reasoning, text generation                       |
| Zhipu AI   | glm-5.2                      | Reasoning, text generation                       |
| DeepSeek   | deepseek-v4-pro              | Reasoning, text generation                       |
| DeepSeek   | deepseek-v4-pro-0813         | Reasoning, text generation                       |
| DeepSeek   | deepseek-v4-flash-0731       | Reasoning, text generation                       |
| DeepSeek   | deepseek-v4.1-flash          | Reasoning, visual understanding, text generation |
| DeepSeek   | deepseek-v4.1-flash-1017     | Reasoning, visual understanding, text generation |
| Wan        | wan2.7-image                 | Image generation                                 |
| Wan        | wan2.7-image-pro             | Image generation                                 |
| Wan        | wan3.0-video                 | Video generation                                 |
| HappyHorse | happyhorse-1.1-i2v           | Video generation                                 |
| HappyHorse | happyhorse-1.1-t2v           | Video generation                                 |
| HappyHorse | happyhorse-1.1-r2v           | Video generation                                 |

## Supported built-in model tools

Built-in model tools are model-native capabilities, auto-triggered through the Responses API during model calls and deducted from Credits; no separate integration is needed.

| Capability           | Tool name          |
| -------------------- | ------------------ |
| Web search           | web\_search        |
| Text-to-image search | web\_search\_image |
| Reverse image search | image\_search      |
| Web scraping         | web\_extractor     |
| Code interpreter     | code\_interpreter  |

## Plans and pricing

|                       | Lite                                                                                                                     | Essential                                                                                | Standard               | Pro                                           | Credit Pack                                                                               |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- | ---------------------- | --------------------------------------------- | ----------------------------------------------------------------------------------------- |
| **Price**             | **\$6**/month<br />[Limited-time new-user price](#tpp01-h-new-user-promo) **\$3**/month                                  | **\$10**/month<br />[Limited-time new-user price](#tpp01-h-new-user-promo) **\$5**/month | **\$18**/month         | **\$43**/month                                | \$15/pack/month<br />20,000 Credits/pack<br />Up to 5 at a time                           |
| **Monthly quota**     | 20,000 Credits                                                                                                           | 45,000 Credits                                                                           | 80,000 Credits         | 200,000 Credits                               | Does not count toward plan quota                                                          |
| **Concurrent agents** | 1-2                                                                                                                      | 2-3                                                                                      | 3-4                    | 6-8                                           | -                                                                                         |
| **Features**          | Text, vision, and multimodal models<br />Web search and other built-in model tools<br />Compatible with mainstream tools | All Lite features                                                                        | All Essential features | All Standard features<br />Higher concurrency | Does not count toward plan quota<br />Requires active subscription<br />Up to 5 at a time |

See the [Token Plan pricing page](https://www.qwencloud.com/pricing/token-plan) for current pricing. Credit Packs can be purchased from the [Token Plan Individual page](https://home.qwencloud.com/analytics/token-plan/individual) in the console.

- **Monthly quota**: The quota is calculated per subscription month. When the plan quota is used up and no Credit Pack Credits are available, the service is paused until the next subscription month.
- **Credit Pack**: Priced at \$15/pack/month, with 20,000 Credits per pack. Requires an active subscription before purchase, hold up to 5 at the same time; after the plan's monthly quota is used up, Credit Pack Credits are deducted automatically.
- **Quota adjustment**: Starting November 9, 2026 at 20:00 (UTC+8), monthly quotas increase for all four Token Plan Individual plans, and the Pro plan list price and official discount price are reduced. Existing subscriptions are topped up to the new quota for the current subscription cycle, with used Credits unchanged. The Pro price remains unchanged for the current subscription period; the new price applies from the next subscription period. See the [Token Plan Individual price reduction notice](/changelog/token-plan-credits-1109).

After the monthly quota is used up, you can purchase a Credit Pack for additional Credits, or wait for the quota to reset at the start of the next subscription month. Unused quota within a subscription month does not carry over to the next cycle.

<span id="tpp01-h-new-user-promo" />

<Note>
  The limited-time new-user price is available until 23:59:59 on November 30, 2026 (UTC+8) and is limited to accounts that have never purchased a Token Plan Individual subscription.
</Note>

## Credits billing mechanism

<Note>
  Multimodal models such as video generation consume significantly more Credits per call than text conversations. Pay attention to the following two points:

  - **High consumption per call**: Credits for video generation increase with the duration and resolution, which may quickly use up a large part of your quota. For your first attempts, use a shorter duration and a lower resolution, check the actual consumption per call in **Model usage** on the [Token Plan](https://home.qwencloud.com/analytics/token-plan/individual) page, and then decide on further usage.
  - **Batch settlement for asynchronous tasks**: Credits for asynchronous tasks such as video generation are settled after the task completes, rather than deducted at submission. If you submit multiple asynchronous tasks within a short period, the Credits settled together after all the tasks complete may cause you to reach the quota limit quickly.
</Note>

### Billing description

The Credits consumed per request are dynamically determined by model type, token usage, thinking mode, and tool calls. Refer to **Model usage** on the [Token Plan](https://home.qwencloud.com/analytics/token-plan/individual) page for actual consumption.

### Deduction order

1. Credits consumed by each call are deducted from the plan quota of the current subscription month first.
2. After the plan's monthly quota is used up, Credit Pack Credits are automatically deducted. When Credit Pack Credits are also used up or not held, the service is paused. You can upgrade to a higher-tier plan, or wait for the quota to reset at the start of the next subscription month.

### Quota reset

The quota resets automatically per subscription month: at the start of each subscription month, the plan quota is restored to the full monthly quota of the corresponding tier. When the weekly quota was removed on September 22, 2026, the remaining quota of existing subscriptions was reset once to the full monthly quota of their plan tier on that day, with subscription periods and expiration dates unchanged.

## Getting started

See the [Quick start](/token-plan/personal/token-plan-personal-quickstart) guide to subscribe, get your API Key, and set up your AI tool in three steps.

## Subscription management

### Upgrade

You can upgrade from a lower plan to a higher one. Go to the [Token Plan pricing page](https://www.qwencloud.com/pricing/token-plan) to select a target plan. Upgrades do not reset the current subscription cycle: you pay the prorated price difference for the remaining days of the current cycle, the current cycle only receives additional Credits prorated based on the quota difference, and the new tier's monthly quota applies from the next subscription month.

The Credits granted upon upgrade are not the full monthly quota of the new plan tier. Instead, they are prorated based on the price difference you actually paid and the number of days remaining in your current billing cycle:

```plaintext
Upgrade price difference = (New plan price − Old plan price) × Remaining days / 30
(Less than one day counts as one day)

Additional quota for the current cycle = Remaining days / 30 × (Monthly quota after upgrade − Monthly quota before upgrade)
(Less than one day counts as one day; the result is rounded up)
```

The actual upgrade fee is subject to the price breakdown shown on the payment page.

### Renewal

You can switch renewal periods and renew for multiple cycles at once.

- **Manual renewal**: Choose a different renewal period and renew for multiple cycles.
- **Auto-renewal**: When enabled, the system automatically charges and renews before expiration.

Renewal extends the subscription period only and does not add quota to the current billing cycle.

### Other

- Individual does not currently support cancellation.
- If your subscription expires, your API Key becomes unavailable; after you repurchase, the original API Key becomes usable again and no reconfiguration is required in your tools.

## Before you subscribe

- **Device usage**: You can configure the same API Key on multiple devices you own (such as your home and office computers), but the Individual plan is for your exclusive use. Sharing the API Key with others may be considered a violation and result in suspension.

## Terms of use

1. **Usage scope**: Use is limited to interactive use within programming and agent tools (such as Claude Code, Cursor, Qwen Code, Qoder, OpenClaw, etc.). It must not be used for automation scripts, custom application backends, or any non-interactive batch call scenarios. Models are accessed through the tools' extension mechanisms (Skill, Slash Command, or Agent); calls initiated interactively within a tool are considered normal use. Using the API Key for calls outside the allowed scope will be considered a violation or abuse, and may result in subscription suspension or API Key banning.
2. **Region and data transfer**: For Token Plan, the only available region is Singapore and the only available deployment mode is Global, which means the model inference will be performed globally. The prompts and model outputs will involve cross-border data transfer, and you are responsible for ensuring that your use of the Token Plan complies with applicable laws and regulations.
3. **Account rules**: The subscription is for the subscriber's personal use only. Sharing is prohibited and may result in restricted access.
4. **Purchase limit**: One subscription per account. You can hold both Individual and Team Edition simultaneously.