Configure SenseNova

SenseNova is a large language model series launched by SenseTime, providing the SenseChat series models. It supports multimodal capabilities, excels at Chinese understanding and generation, and supports personal users after identity verification, providing free quotas.

Platform Description: After logging in, you will see "SenseNova Model Development Platform" or "SenseTime Platform" wording. This is SenseTime's unified development platform brand, where SenseNova large models are deployed.

1. Obtain SenseNova API Key

1.1 Visit SenseNova Open Platform

Visit the SenseNova Open Platform and log in: https://platform.sensenova.cn/

Note: The platform interface shows "SenseNova Model Development Platform", which is the correct platform where the SenseNova model API is obtained.

1.2 Complete Identity Verification

First-time use requires personal identity verification:

1. Click Identity Verification in the upper right corner
2. Select Identity Verification from the left menu
3. Select "Start Personal Verification" on the page, fill in identity information and submit

1.3 Enter API Keys Page

After verification is approved, click API Keys in the left menu to enter the key management page.

1.4 Create New API Key

Click the Create API-Key (1/20) button in the upper right corner.

Note: When you register an account and enter, there will be a default key data named "apikey-2025xxxxxxx".

1.5 Set API Key Information

In the popup dialog:

1. Enter the API Key name (e.g., CueMate)
2. Click the Save button

1.6 Copy API Key

After successful creation, the system will display the API Key.

Important: This is the only time you can see the complete API Key, please copy and save it immediately.

Click the copy button, and the API Key has been copied to the clipboard.

2. Configure SenseNova Model in CueMate

2.1 Enter Model Settings Page

After logging into CueMate, click Model Settings in the dropdown menu in the upper right corner.

2.2 Add New Model

Click the Add Model button in the upper right corner.

2.3 Select SenseNova Provider

In the popup dialog:

1. Provider Type: Select SenseNova
2. After clicking, it will automatically proceed to the next step

2.4 Fill in Configuration Information

Fill in the following information on the configuration page:

Basic Configuration

1. Model Name: Give this model configuration a name (e.g., SenseChat-5)
2. API URL: Keep the default https://api.sensenova.cn
3. API Key: Paste the SenseNova API Key you just copied
4. Model Version: Select the model ID you want to use. Common models include:
   • SenseNova-V6-5-Pro: Latest V6.5 flagship model, strongest capability
   • SenseNova-V6-5-Turbo: V6.5 fast model, high cost-performance
   • SenseChat-5: SenseChat 5.0 flagship model
   • Qwen3-Coder: Qwen code model
   • And 18 other models (see complete list below)

Advanced Configuration (Optional)

Expand the Advanced Configuration panel to adjust the following parameters:

CueMate Interface Adjustable Parameters:

1. Temperature: Controls output randomness

   • Range: 0-1
   • Recommended Value: 0.7
   • Function: Higher values produce more random and creative output, lower values produce more stable and conservative output
   • Usage Suggestions:
     • Creative writing/brainstorming: 0.8-1.0
     • Regular conversation/Q&A: 0.6-0.8
     • Code generation/precise tasks: 0.3-0.5

2. Max Tokens: Limits single output length

   • Range: 256 - 16384
   • Recommended Value: 4096
   • Function: Controls the maximum word count of model's single response
   • Model Limits:
     • SenseNova-V6.5-Pro: max 16K tokens
     • SenseNova-V6.5-Turbo: max 16K tokens
   • Usage Suggestions:
     • Short Q&A: 1024-2048
     • Regular conversation: 4096-8192
     • Long text generation: 8192-16384

Other Advanced Parameters Supported by SenseNova API:

Although CueMate's interface only provides temperature and max_tokens adjustments, if you call SenseNova directly through the API, you can also use the following advanced parameters (SenseNova uses OpenAI-compatible API format):

3. top_p (nucleus sampling)

   • Range: 0-1
   • Default Value: 0.95
   • Function: Samples from the smallest candidate set with cumulative probability reaching p
   • Relationship with temperature: Usually only adjust one of them
   • Usage Suggestions:
     • Maintain diversity but avoid absurdity: 0.9-0.95
     • More conservative output: 0.7-0.8

4. repetition_penalty

   • Range: 1.0-2.0
   • Default Value: 1.0
   • Function: Penalizes generated tokens to reduce repetition
   • Usage Suggestions:
     • Reduce repetition: 1.1-1.3
     • Allow repetition: 1.0 (default)

5. stream

   • Type: Boolean
   • Default Value: false
   • Function: Enables SSE streaming return, returning as it generates
   • In CueMate: Handled automatically, no manual setting required

No.	Scenario	temperature	max_tokens	top_p	repetition_penalty
1	Creative writing	0.8-1.0	4096-8192	0.95	1.1
2	Code generation	0.2-0.5	2048-4096	0.9	1.0
3	Q&A system	0.7	1024-2048	0.9	1.0
4	Long text generation	0.6-0.8	8192-16384	0.9	1.1

2.5 Test Connection

After filling in the configuration, click the Test Connection button to verify if the configuration is correct.

If the configuration is correct, it will display a success message and return a model response example.

2.6 Save Configuration

After a successful test, click the Save button to complete the model configuration.

3. Use Model

Through the dropdown menu in the upper right corner, enter the system settings interface and select the model configuration you want to use in the Large Model Provider section.

After configuration, you can select to use this model in functions such as interview training and question generation, or you can individually select the model configuration for a specific interview in the interview options.

4. Supported Model List

Description: The SenseNova platform provides a rich selection of models, including self-developed SenseNova and SenseChat series, as well as third-party models such as Qwen, Kimi, DeepSeek, etc.

4.1 SenseNova V6 Series (Recommended)

No.	Model Name	Model ID	Max Output	Use Case
1	SenseNova-V6-5-Omni	SenseNova-V6-5-Omni	8K tokens	Full-modal interaction, real-time dialogue, multimodal understanding
2	SenseNova-V6-5-Pro	SenseNova-V6-5-Pro	16K tokens	Latest flagship model, complex tasks, deep understanding
3	SenseNova-V6-5-Turbo	SenseNova-V6-5-Turbo	16K tokens	High-performance fast model, cost-performance priority
4	SenseNova-V6-Reasoner	SenseNova-V6-Reasoner	8K tokens	Reasoning tasks, logical analysis, deep thinking
5	SenseNova-V6-Turbo	SenseNova-V6-Turbo	8K tokens	V6 fast version, daily conversations

4.2 SenseChat Series

No.	Model Name	Model ID	Max Output	Use Case
1	SenseChat-5	SenseChat-5	8K tokens	SenseChat 5.0 flagship, complex tasks
2	SenseChat-5-Cantonese	SenseChat-5-Cantonese	8K tokens	Cantonese conversation, dialect understanding
3	SenseChat-128K	SenseChat-128K	8K tokens	Ultra-long context, long text processing
4	SenseChat-32K	SenseChat-32K	8K tokens	Long context conversations
5	SenseChat-Turbo	SenseChat-Turbo	4K tokens	Fast response, high cost-performance
6	SenseChat	SenseChat	4K tokens	Basic conversation model
7	SenseChat-Vision	SenseChat-Vision	4K tokens	Visual understanding, image-text dialogue
8	SenseChat-Character	SenseChat-Character	4K tokens	Role-playing, personalized conversations
9	SenseChat-Character-Pro	SenseChat-Character-Pro	4K tokens	Advanced role-playing

4.3 Third-Party Models

No.	Model Name	Model ID	Max Output	Use Case
1	Qwen3-Coder	Qwen3-Coder	8K tokens	Code generation, programming assistance
2	Qwen2-5-Coder	Qwen2-5-Coder	8K tokens	Qwen code model 2.5
3	Qwen3-235B	Qwen3-235B	8K tokens	Qwen 3 ultra-large model
4	Qwen3-32B	Qwen3-32B	8K tokens	Qwen 3 standard model
5	Qwen2-72B	Qwen2-72B	8K tokens	Qwen 2 large model
6	Qwen2-7B	Qwen2-7B	8K tokens	Qwen 2 lightweight model
7	DeepSeek-V3-1	DeepSeek-V3-1	8K tokens	DeepSeek third generation model
8	Kimi-K2	Kimi-K2	8K tokens	Moonshot AI Kimi model

5. Common Issues

5.1 Invalid API Key

Symptom: API Key error prompt during test connection

Solution:

1. Check if the API Key format is correct
2. Confirm that identity verification has been approved
3. Check if the account has available quota

5.2 Request Timeout

Symptom: No response for a long time during test connection or usage

Solution:

1. Check if network connection is normal
2. Confirm API URL address is correct: https://api.sensenova.cn
3. Check firewall settings

5.3 Insufficient Quota

Symptom: Prompt that quota is exhausted or insufficient balance

Solution:

1. Log in to SenseNova platform to check account balance
2. Recharge or apply for more quota
3. Optimize usage frequency

Related Links

• SenseNova Official Website
• Open Platform
• API Documentation
• Pricing Information