ANanam
LLMs

create llm

Changed on

Create a new LLM configuration

post/v1/llms

Request

  • Base URL
    https://api.anam.ai
  • URL
    https://api.anam.ai/v1/llms
  • Auth
    HTTP bearer

Request body

displayNamestring required
descriptionstring
llmFormat'openai' | 'azure_openai' | 'groq_openai' | 'gemini' | 'none' required
modelNamestring required
secretstring required
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). Omit or set null to use the model default.

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

Groq reasoning format hint. Omit or set null to use the model default.

Example request

{
  "reasoningEffort": "minimal"
}

Response

Successfully created 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' | '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.

isDeprecatedboolean

Whether this stock LLM is deprecated. Deprecated LLMs remain available to ephemeral sessions but cannot be newly assigned to personas.

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.

Changes

  • e85ef0cd491eRevision changes
    • info

      added the non-success response with the status

  • dc7e31f03c66Revision changes
    • breaking

      removed the enum value advanced_voice of the request property

    • info

      removed the advanced_voice enum value from the response property for the response status