ModelScope

What is ModelScope?

ModelScope is a new-generation open-source Model-as-a-Service (MaaS) sharing platform, dedicated to providingflexible, easy-to-use, low-costa one-stop model service solution, making model application easier!

Through API-Inference service capabilities, the platform standardizes open-source models into callable API interfaces, allowing developers to lightweightly and quickly integrate model capabilities into various AI applications, supporting innovative scenarios such as tool calling and prototype development.

Core advantages

• ✅ Free quota: Provides daily 2,000 free API calls(Billing rules)
• ✅ Rich model library: Covers 1,000+ open-source models across NLP, CV, speech, multimodal, and more
• ✅ Ready to use out of the box: No deployment required, call quickly through RESTful API

---

Cherry Studio integration process

Step 1: Get a ModelScope API token

1. Log in to the platform

   • Access ModelScope official website → click the top rightLog in → choose an authentication method
2. Create an access token

   • Enter Account settings → Access tokens
   • Click Create new token → fill in a description → Copy the generated token(See the example page below)

   🔑 Important note: Token leakage will compromise account security!

Step 2: Configure Cherry Studio

• Open Cherry Studio → Settings → Model services → ModelScope
• in API key Paste the copied token into the field
• Click Save Complete authorization

Step 3: Call the model API

1. Find models that support API

   • Access ModelScope model library
   • Filter criteria:Check API-Inference(or look for the API icon)

   The range of models covered by API-Inference is mainly determined by the level of attention a model receives in the ModelScope community (based on data such as likes and downloads). Therefore, after a next-generation open-source model with stronger capabilities and higher attention is released, the list of supported models will continue to be updated.

2. Get the model ID

   • Enter the target model detail page → copy Model ID(format such as damo/nlp_structbert_sentiment-classification_chinese-base)
3. Fill in Cherry Studio

   • On the model service configuration page, the Model ID field, enter the ID → choose the task type → finish configuration

---

Billing and quota rules

Important note

• 🎫 Free quota: Each user 2,000 API calls per day(*subject to the latest rules on the official website)
• 🔁 Quota reset: Automatically resets daily at 00:00 UTC+8,does not support cross-day accumulation or rollover
• 💡 Over-limit handling:

  • After reaching the daily limit, the API will return 429 error
  • Solution: switch to a backup account / use another platform / optimize call frequency

View remaining quota

• Log in to ModelScope → click the top right Username → API usage

⚠️ Note: Inference API-Inference has a free quota of 2,000 calls per day. For more call needs, consider cloud services such as Alibaba Cloud Bailian.

---

💡 Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions the official channels provided there.