Qwen
Billing unit
Model service | Billing unit |
Qwen-110B | token |
Qwen-72B | token |
Qwen-32B | token |
Qwen-14B | token |
Qwen-7B | token |
A token is the basic unit used by models to represent text in natural languages. A token can be considered as a character or word. In most cases, a token corresponds to a character in Chinese text or three to four letters in English text.
Qwen calculates the number of input and output tokens consumed by a model call and generates bills based on the number of consumed tokens. The number of input tokens is also calculated based on the historical conversations of multi-round conversations. You can obtain the number of tokens consumed during a model call from the response returned by the model.
Unit price
Model | Name | Unit price of input tokens | Unit price of output tokens | Billing method | Release date |
Qwen-110B | qwen1.5-110b-chat | $0.004/1000 tokens | $0.012/1000 tokens | Pay-as-you-go | Released |
Qwen-72B | qwen1.5-72b-chat | $0.003/1000 tokens | $0.009/1000 tokens | Pay-as-you-go | Released |
Qwen-32B | qwen1.5-32b-chat | Free for a limited period | Free for a limited period | Pay-as-you-go | Released |
Qwen-14B | qwen1.5-14b-chat | Free for a limited period | Free for a limited period | Pay-as-you-go | Released |
Qwen-7B | qwen1.5-7b-chat | Free for a limited period | Free for a limited period | Pay-as-you-go | Released |
Throttling thresholds
To ensure fair access to models, Qwen sets throttling thresholds for regular users. If a throttling threshold is reached, your API request for a model fails due to throttling. You must wait for a period of time until your usage falls back within the throttling threshold before you can call the model again.
Throttling is model-specific and is associated with the Alibaba Cloud account from which a model is called. Throttling is applied based on the total number of calls that are initiated to the model by using all API keys within the Alibaba Cloud account.
If you want to increase the throttling thresholds for a model, click the link in the following table to submit a request.
Model | Name | Throttling threshold |
Qwen-110B | qwen1.5-110b-chat | The throttling policy may change when time-limited free quotas are available. Throttling is triggered if one of the following throttling thresholds is reached:
|
Qwen-72B | qwen1.5-72b-chat | Throttling is triggered if one of the following throttling thresholds is reached:
|
Qwen-32B | qwen1.5-32b-chat | Throttling is triggered if one of the following throttling thresholds is reached:
|
Qwen-14B | qwen1.5-14b-chat | Throttling is triggered if one of the following throttling thresholds is reached:
|
Qwen-7B | qwen1.5-7b-chat | Throttling is triggered if one of the following throttling thresholds is reached:
|