v4

latestOpenAPI 3.1.02026-08-086635375.7 KB
LLMs

update llm

Update an LLM configuration

put/v1/llms/{id}

Path parameters

idstring required

The LLM ID

Request body

displayNamestring
descriptionstring
urlstring
llmFormat'openai' | 'azure_openai' | 'groq_openai' | 'anthropic' | 'custom'
modelNamestring
secretstring
metadataobject
reasoningEffortstring nullable

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). Set null to clear and use the model default.

reasoningFormat'parsed' | 'hidden' | 'null' nullable

Groq reasoning format hint. Set null to clear and use the model default.

Example request

{
  "reasoningEffort": "minimal"
}

Response

Successfully updated LLM

idstring uuid

Unique identifier for the LLM configuration.

displayNamestring

Human-readable name shown in the Lab.

descriptionstring nullable

Free-form description of the LLM configuration.

llmFormat'openai' | 'azure_openai' | 'groq_openai' | 'gemini' | 'advanced_voice' | 'none'

Wire format used to call the upstream LLM.

modelNamestring nullable

Upstream model identifier (e.g. gpt-4o).

temperaturenumber nullable

Sampling temperature applied when calling the LLM.

maxTokensinteger nullable

Maximum tokens generated per response.

deploymentNamestring nullable

Azure OpenAI deployment name. Only used when llmFormat is azure_openai.

apiVersionstring nullable

Azure OpenAI API version. Only used when llmFormat is azure_openai.

metadataobject

Free-form provider-specific metadata.

displayTagsstring[]

Tags used to categorise the LLM in the Lab UI.

isDefaultboolean

Whether this LLM is a built-in default available to every organization.

isGlobalboolean

Whether this LLM is visible to every organization.

isZdrboolean

Whether this LLM meets the Zero Data Retention requirements.

reasoningEffortstring nullable

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.

reasoningFormat'parsed' | 'hidden' | 'null' nullable

Reasoning format hint for models that accept it. Null means the model default is used.

createdByOrganizationIdstring nullable

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.

createdAtstring date-time

Timestamp when the LLM was created.

updatedAtstring date-time nullable

Timestamp when the LLM was last updated.