Generate Dialogue (Click to View Details)
Analyze an Image (Click to View Details)
Generate JSON Data (Click for Details)
Message Type | Function Description | Example Content |
---|---|---|
system | Model instructions, defining the AI’s role and general behavior | e.g., “You are a pediatrician with 10 years of experience.” |
user | User input, passing the end user’s message to the model | e.g., “How should a persistent fever in a toddler be treated?“ |
assistant | Model-generated historical responses, providing examples of how it should respond to the current request | e.g., “I suggest measuring the temperature first…” |
temperature
, top_k
, top_p
, and frequency_penalty
.
Corresponding payload adjustments for different languages:
max_tokens
For the LLM models provided by the platform:
16384
:
8192
:
max_tokens
limit of 4096
include:
context_length
The context_length
varies across different LLM models. You can search for specific models on the Models to view detailed information.
4. Model Output Truncation Issues
To troubleshoot truncation issues:
max_tokens
to an appropriate value. Outputs exceeding max_tokens
will be truncated. The DeepSeek R1 series supports up to 16384 tokens.max_tokens=4096
. Users can enable the “Message Length Limit” switch in settings to adjust the value.Error Code | Common Cause | Solution |
---|---|---|
400 | Parameter format error | Check the range of parameters like temperature |
401 | API Key not correctly set | Verify the API Key |
403 | Insufficient permissions | Commonly requires real-name authentication; refer to error messages for other cases |
429 | Request rate limit exceeded | Implement exponential backoff retry mechanism |
503/504 | Model overload | Switch to backup model nodes |
Total Cost = (Input Tokens × Input Unit Price) + (Output Tokens × Output Unit Price)