OBxChat

Providers Supporting This Model

Spark
SparkSpark
Spark4.0Ultra
Max Context Length
8K
Max Response Length
8K
Input Cost
--
Output Cost
--
Higress
Spark4.0Ultra
Max Context Length
8K
Max Response Length
8K
Input Cost
--
Output Cost
--

Model Settings

Creativity Level
temperature

Controls creativity. 0 = predictable responses, higher = more varied and unexpected results. View Documentation

Type
FLOAT
Default
1.00
Range
0.00 ~ 2.00
Response Diversity
top_p

Filters responses to the most likely words within a probability range. Lower values keep answers more focused. View Documentation

Type
FLOAT
Default
1.00
Range
0.00 ~ 1.00
New Idea Encouragement
presence_penalty

Encourages or discourages using new words. Higher values promote fresh ideas, while lower values allow more reuse. View Documentation

Type
FLOAT
Default
0.00
Range
-2.00 ~ 2.00
Repetition Control
frequency_penalty

Adjusts how often the model repeats words. Higher values mean fewer repeats, while lower values allow more repetition. View Documentation

Type
FLOAT
Default
0.00
Range
-2.00 ~ 2.00
Response Length Limit
max_tokens

Sets the max length of responses. Increase for longer replies, decrease for shorter ones. View Documentation

Type
INT
Default
--
Range
0 ~ 8K
Reasoning Depth
reasoning_effort

Determines how much effort the model puts into reasoning. Higher settings generate more thoughtful responses but take longer. View Documentation

Type
STRING
Default
--
Range
low ~ high

Related Models

Spark

Spark Lite

lite
Spark Lite is a lightweight large language model with extremely low latency and efficient processing capabilities, completely free and open, supporting real-time online search functionality. Its quick response feature makes it excel in inference applications and model fine-tuning on low-power devices, providing users with excellent cost-effectiveness and intelligent experiences, particularly in knowledge Q&A, content generation, and search scenarios.
8K
Spark

Spark Pro

generalv3
Spark Pro is a high-performance large language model optimized for professional fields, focusing on mathematics, programming, healthcare, education, and more, supporting online search and built-in plugins for weather, dates, etc. Its optimized model demonstrates excellent performance and efficiency in complex knowledge Q&A, language understanding, and high-level text creation, making it an ideal choice for professional application scenarios.
8K
Spark

Spark Pro 128K

pro-128k
Spark Pro 128K is equipped with an extra-large context processing capability, able to handle up to 128K of contextual information, making it particularly suitable for long-form content that requires comprehensive analysis and long-term logical connections, providing smooth and consistent logic and diverse citation support in complex text communication.
128K
Spark

Spark Max

generalv3.5
generalv3.5.description
8K
Spark

Spark Max 32K

max-32k
Spark Max 32K is configured with large context processing capabilities, enhanced contextual understanding, and logical reasoning abilities, supporting text input of 32K tokens, suitable for long document reading, private knowledge Q&A, and other scenarios.
32K