seg_yinzy
/
dify-docs
mirror of https://github.com/langgenius/dify-docs.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

GITBOOK-27: change request with no subject merged in GitBook

pull/29/head
潘辉燕 2023-12-13 03:28:18 +00:00 committed by gitbook-bot
parent 6bdf387722
commit 1bc66f7020
No known key found for this signature in database
GPG Key ID: 07D2180C7B12D0FF
1 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
en/workspace/billing.md
View File

@ -22,10 +22,18 @@ Workspace 2
We offer a free plan for all users to test your AI app ideas, including 200 OpenAI model message calls. After using up the free allowance, you need to obtain LLM API keys from different model providers, and add them under **Settings --> Model Providers** to enable normal model capabilities.Upgrading your workspace to a paid plan means unlocking paid resources for that workspace. For example: upgrading to Professional allows creating over 10 apps (up to 50) with up to 200MB total vector storage quota combined across projects in that workspace. Different version quotas and features are as follows:
<table><thead><tr><th width="148">Metric</th><th width="237">Sandbox</th><th>Professional </th><th>Team</th></tr></thead><tbody><tr><td>pricing</td><td>Free</td><td>$59/month</td><td>$159/month</td></tr><tr><td><strong>Model Providers</strong></td><td>OpenAI,Anthropic,Azure OpenAI,Llama2,Hugging Face,Replicate</td><td>OpenAI,Anthropic,Azure OpenAI, Llama2,Hugging Face,Replicate</td><td>OpenAI,Anthropic,Azure OpenAI, Llama2,Hugging Face,Replicate</td></tr><tr><td><strong>Team Members</strong></td><td>1</td><td>3</td><td>Unlimited</td></tr><tr><td><strong>Apps</strong></td><td>10</td><td>50</td><td>Unlimited</td></tr><tr><td><strong>Vector Storage</strong></td><td>10MB</td><td>200MB</td><td>1GB</td></tr><tr><td><strong>Document Processing Priority</strong></td><td>Standard</td><td>Priority</td><td>Priority</td></tr><tr><td><strong>Logo Change</strong></td><td>/</td><td>/</td><td>√</td></tr><tr><td><strong>Fine-Tuning</strong></td><td>/</td><td>√(Coming soon)</td><td>√(Coming soon)</td></tr><tr><td><strong>Logs History</strong></td><td>30 days</td><td>Unlimited</td><td>Unlimited</td></tr></tbody></table>
<table><thead><tr><th width="148">Metric</th><th width="237">Sandbox</th><th>Professional </th><th>Team</th></tr></thead><tbody><tr><td>pricing</td><td>Free</td><td>$59/month</td><td>$159/month</td></tr><tr><td><strong>Model Providers</strong></td><td>OpenAI,Anthropic,Azure OpenAI,Llama2,Hugging Face,Replicate</td><td>OpenAI,Anthropic,Azure OpenAI, Llama2,Hugging Face,Replicate</td><td>OpenAI,Anthropic,Azure OpenAI, Llama2,Hugging Face,Replicate</td></tr><tr><td><strong>Team Members</strong></td><td>1</td><td>3</td><td>Unlimited</td></tr><tr><td><strong>Apps</strong></td><td>10</td><td>50</td><td>Unlimited</td></tr><tr><td><strong>Vector Storage</strong></td><td>5MB</td><td>200MB</td><td>1GB</td></tr><tr><td><strong>Document Processing Priority</strong></td><td>Standard</td><td>Priority</td><td>Priority</td></tr><tr><td><strong>Logo Change</strong></td><td>/</td><td>/</td><td>√</td></tr><tr><td><strong>API Requests Quota Limits</strong></td><td>500 per day</td><td>Unlimited</td><td>Unlimited</td></tr><tr><td><strong>RAG API Requests Quota Limits</strong></td><td>/</td><td>√coming soon</td><td>√coming soon</td></tr><tr><td><strong>Annotated Response Quota Limits</strong></td><td>10</td><td>2000</td><td>5000</td></tr><tr><td><strong>Agent Model</strong></td><td>/</td><td>√coming soon</td><td>√coming soon</td></tr><tr><td><strong>Logs History</strong></td><td>30 days</td><td>Unlimited</td><td>Unlimited</td></tr></tbody></table>
Check out the [pricing page ](https://dify.ai/pricing)to learn more.
> **Vector storage:**Vector storage is used to store knowledge bases as vectors for LLMs to understand. Each 1MB can store about 1.2million characters of vectorized data(estimated using OpenAI Embeddings, varies across models). How much the data shrinks depends on complexity and repetition in the content.
>
> **Annotated Response:**The annotation feature lets you manually edit the replies to get customizable, high-quality question-answering. When turning this on in chat apps, there are limits on how many human edits you can make.
>
> **API Requests:**The number of times the Dify API is called per day through direct API requests or during web sessions. This counts how often you invoke Dify services via API, rather than LLM API resource consumption. **Note:Daily quotas are refreshed at midnight Pacific Standard Time.**
>
> **RAG API Requests:**Refers to the number of API calls invoking only the knowledge base processing capabilities of Dify.
## Monitor Resource Usage
You can view capacity usage details on your workspace's Billing page.