Ctrl K
Back to Discovery
Moonshot V1 32K offers medium-length context processing capabilities, able to handle 32,768 tokens, particularly suitable for generating various long documents and complex dialogues, applicable in content creation, report generation, and dialogue systems.
32K
models.supportedProviders
models.parameterList.title
models.parameterList.temperature.title
temperature
models.parameterList.temperature.desc models.parameterList.docs
models.parameterList.type
FLOATmodels.parameterList.defaultValue
1.00
models.parameterList.range
0.00 ~ 2.00
models.parameterList.top_p.title
top_p
models.parameterList.top_p.desc models.parameterList.docs
models.parameterList.type
FLOATmodels.parameterList.defaultValue
1.00
models.parameterList.range
0.00 ~ 1.00
models.parameterList.presence_penalty.title
presence_penalty
models.parameterList.presence_penalty.desc models.parameterList.docs
models.parameterList.type
FLOATmodels.parameterList.defaultValue
0.00
models.parameterList.range
-2.00 ~ 2.00
models.parameterList.frequency_penalty.title
frequency_penalty
models.parameterList.frequency_penalty.desc models.parameterList.docs
models.parameterList.type
FLOATmodels.parameterList.defaultValue
0.00
models.parameterList.range
-2.00 ~ 2.00
models.parameterList.max_tokens.title
max_tokens
models.parameterList.max_tokens.desc models.parameterList.docs
models.parameterList.type
INTmodels.parameterList.defaultValue
--
Moonshot V1 8K
moonshot-v1-8k
Moonshot V1 8K is designed for generating short text tasks, featuring efficient processing performance, capable of handling 8,192 tokens, making it ideal for brief dialogues, note-taking, and rapid content generation.
8K
Moonshot V1 128K
moonshot-v1-128k
Moonshot V1 128K is a model with ultra-long context processing capabilities, suitable for generating extremely long texts, meeting the demands of complex generation tasks, capable of handling up to 128,000 tokens, making it ideal for research, academia, and large document generation.
128K