v4
latestOpenAPI 3.1.02026-08-086635375.7 KBcreate llm
Create a new LLM configuration
Request body
Reasoning effort for models that accept it. The value is forwarded verbatim to the provider/engine (e.g. default, none, minimal, low, medium, high, xhigh — supported values depend on the model). Omit or set null to use the model default.
Groq reasoning format hint. Omit or set null to use the model default.
Example request
{
"reasoningEffort": "minimal"
}Response
Successfully created LLM
Unique identifier for the LLM configuration.
Human-readable name shown in the Lab.
Free-form description of the LLM configuration.
Wire format used to call the upstream LLM.
Upstream model identifier (e.g. gpt-4o).
Sampling temperature applied when calling the LLM.
Maximum tokens generated per response.
Azure OpenAI deployment name. Only used when llmFormat is azure_openai.
Azure OpenAI API version. Only used when llmFormat is azure_openai.
Free-form provider-specific metadata.
Tags used to categorise the LLM in the Lab UI.
Whether this LLM is a built-in default available to every organization.
Whether this LLM is visible to every organization.
Whether this LLM meets the Zero Data Retention requirements.
Reasoning effort hint for models that accept it. Forwarded verbatim to the provider/engine; supported values depend on the model. Null means the model default is used.
Reasoning format hint for models that accept it. Null means the model default is used.
ID of the organization that created the LLM, or null for global defaults. IDs may be either UUIDs or nanoid-style strings depending on when the organization was created.
Timestamp when the LLM was created.
Timestamp when the LLM was last updated.