Get a prompt version

GET/v1/prompts/{slug}/versions/{versionRef}

Get a prompt version.

Returns one version with its messages and labels. Requires membership of the prompt's workspace (organization admins have it).

Errors: 400 when versionRef is not a number, latest or @label; 404 when the prompt, version or label does not exist.

Authorization

AuthorizationBearer va_
A platform API key (va_...), created under Settings > API keys. Scoped to an organization or one workspace, with an admin or member role. Used by the management API.

Path parameters

slugstringrequired
the prompt's slug
versionRefstringrequired
which version: a version number (for example 3), latest (the highest number, whatever its status) or @ and a label (for example @staging)

Query parameters

organizationstringrequired
slug of the organization that owns it

Responses

200application/json

idstring
The version's unique id (UUID).
prompt_idstring
Id (UUID) of the prompt the version belongs to.
version_numberinteger<int32>
The version's number within the prompt, from 1, incremented by every save or rollback.
messagesobject[]
The template messages, in order. A message's content may contain {{name}} placeholders.
Child attributes
- roleenum<string>required
  Who the message is from: system, user, assistant or tool (required).
  One of "system", "user", "assistant", "tool"
- contentstringrequired
  The message text (required). Each {{name}} placeholder is replaced with the value of variable name when the prompt is rendered or run; a placeholder with no value is left as written.
modelstring
The model completions use, for example gpt-4o. Null when none was set: a completion or test run must then send model_override.
temperaturenumber<double>
Sampling temperature sent with every completion of this version. Null when not set (the provider's default applies).
max_tokensinteger<int32>
Maximum number of tokens to generate, sent with every completion of this version. Null when not set.
top_pnumber<double>
Nucleus-sampling value (top_p) sent with every completion of this version. Null when not set.
stopstring[]
Stop sequences sent with every completion of this version. Null or empty when none.
variablesobject[]
The variables the template declares. Descriptive only: rendering substitutes whichever variables a request sends.
Child attributes
- namestringrequired
  The variable's name, as written in {{name}} (required).
- descriptionstring
  What the variable is for. Null when not given.
- default_valuestring
  A suggested value. Informational: it is not substituted when a request leaves the variable out.
- requiredboolean
  Whether callers are expected to supply the variable. Informational, not enforced. Default false.
toolsobject[]
Tool definitions stored with the version. They are stored and returned, but completions of this prompt do not send them to the model.
Child attributes
- typestringrequired
  The tool type: function (required).
- functionobjectrequired
  The function of a stored tool definition, in OpenAI's function-calling format.
  Child attributes
  - namestringrequired
    The function's name (required).
  - descriptionstring
    What the function does, for the model. Null when not given.
  - parametersmap<string, object>
    The function's parameters as a JSON Schema object. Null when not given.
statusenum<string>
Lifecycle state: DRAFT (saved, never published), PUBLISHED (the prompt's published version; at most one at a time) or ARCHIVED (was the published version until another version was published).
One of "DRAFT", "PUBLISHED", "ARCHIVED"
labelsstring[]
Labels currently pointing at this version, for example production. Empty when none.
created_atstring<date-time>
When the version was saved (ISO 8601).
created_bystring
Identifier of the caller (user or API key) that saved the version, or unknown when the caller could not be identified.

VectorAxis is built by GK Labs, a member of NVIDIA Inception.