API Reference
List Models
List all available models, both the base models (Llama-3.1-8b and DeepSeek-R1-8b) and all the private models created by the current user.
Output
ModelInfos
Contains all models available to the current use, both base models and models the you have created your self.
Contains information about a model, including its configuration, training parameters, and metadata.
Model name, this is the name given to to model.
Model id, this is a id generated when the model is created.
Model description, set when the model was created.
Is the model readonly, only the models that you have created can be trained(that is not read only)
The name of the parent model, this is the base model that the model is based on.
The revision number of the current model. It start with 0 and is increase by 1 for every training.
Time stamp of the latest training.
The default model the one selected at startup.
Default temperature setting, this is the value user in getResponse if no other value if specified.
Controls the randomness and creativity of the model's responses. Lower values make output more focused and deterministic, while higher values increase randomness and creativity.
- 0.0 - Most deterministic, repeatable responses
- 1.0 - Balanced creativity and coherence (recommended for most use cases)
- 2.0 - Maximum randomness and creativity
Note: For tasks requiring consistency (like data extraction or classification), use lower values (0.0-0.3). For creative tasks (like brainstorming or storytelling), higher values (0.7-1.5) work better.
Default temperature setting, this is the value user in getResponse if no other value if specified.
Also known as "nucleus sampling," this parameter controls the diversity of responses by limiting the model to consider only the most probable tokens whose cumulative probability reaches the specified threshold.
- 0.1 - Very focused, only highly probable tokens
- 0.5 - Moderately diverse output
- 1.0 - Considers all tokens based on their probability
Note: It's generally recommended to adjust either temperature OR top_p, but not both simultaneously. When top_p is less than 1.0, the model samples from the smallest set of tokens whose cumulative probability exceeds the threshold.
curl http://localhost:45678/v1/models \
-H "Authorization: Bearer $TIGER_API_KEY"{
"beta" : 0.04,
"default_model" : true,
"description" : "LLM for advanced reasoning, math, and code tasks.",
"epsilon" : 0.2,
"id" : "deppseek-r1-8b",
"last_modified" : "2025-02-02T12:34:58.488Z",
"learning_rate" : 0.00001,
"learning_steps" : 5,
"name" : "DeepSeek-R1-8b",
"read_only" : true,
"revision" : 0,
"temperature" : 0.7,
"top_p" : 0.95
}
{
"beta" : 0.04,
"default_model" : false,
"description" : "Multilingual large language model from Meta",
"epsilon" : 0.2,
"id" : "llama-3.1-8b",
"last_modified" : "2025-03-14T13:42:48.942Z",
"learning_rate" : 0.00001,
"learning_steps" : 5,
"name" : "Llama-3.1-8b",
"read_only" : true,
"revision" : 0,
"temperature" : 0.7,
"top_p" : 0.95
}
{
"beta" : 0.8,
"default_model" : false,
"description" : "Base on DeepSeek-R1-8b",
"epsilon" : 0.2,
"id" : "model42",
"last_modified" : "2025-11-11T10:13:14.629Z",
"learning_rate" : 0.00001,
"learning_steps" : 5,
"name" : "Model42",
"parent_model" : "DeepSeek-R1-8b",
"read_only" : false,
"revision" : 1,
"temperature" : 0.7,
"top_p" : 0.95
}
TigerCity.ai