Get a routing config

GET/v1/configs/{slug}

Get a routing config.

Answers the config with its full target tree, conditions and settings.

Requires a key of the organization with access to the config's workspace: a workspace key (member or admin) for that workspace, or an organization admin key. 403 without it; 404 when the organization has no config with this slug.

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 config's slug

Query parameters

organizationstringrequired
the organization slug

Responses

200application/json

idstring<uuid>
The config's id (UUID).
slugstring
The config's slug: send it in the x-config header, and use it to manage the config.
namestring
The config's name, unique within the organization.
descriptionstring
A free-text description. Absent when none was set.
organizationstring
The slug of the organization the config belongs to.
workspace_idstring<uuid>
The workspace the config belongs to (UUID).
strategy_modeenum<string>
How a request picks among targets: SINGLE (the first), LOADBALANCE (at random, by weight), FALLBACK (in order, moving on at a status in on_status_codes) or CONDITIONAL (by conditions).
One of "SINGLE", "LOADBALANCE", "FALLBACK", "CONDITIONAL"
on_status_codesinteger<int32>[]
For FALLBACK: the statuses that move on to the next target. Absent: 429, 500, 502, 503 and 504.
conditional_default_target_namestring
For CONDITIONAL: the target used when no condition matches. Absent: none (such a request fails with 424).
targetsobject[]
The top-level targets in order; nested strategies carry their own targets.
Child attributes
- namestring
  The target's name, which conditions refer to. Absent when none was set.
- virtual_key_slugstring
  For a virtual key target: the key's slug. Absent for a nested strategy target.
- weightnumber<double>
  For LOADBALANCE: the target's share of requests, relative to its siblings. Default 1.
- order_indexinteger<int32>
  The target's position among its siblings (the FALLBACK order).
- strategy_modeenum<string>
  For a nested strategy target: SINGLE, LOADBALANCE, FALLBACK or CONDITIONAL. Absent for a virtual key target.
  One of "SINGLE", "LOADBALANCE", "FALLBACK", "CONDITIONAL"
- on_status_codesinteger<int32>[]
  For a nested FALLBACK target: the statuses that move on to its next target. Absent: the default.
- conditional_default_target_namestring
  For a nested CONDITIONAL target: the target used when no condition matches.
- conditionsobject[]
  For a nested CONDITIONAL target: its rules, in condition_order. Empty otherwise.
  Child attributes
  - condition_orderinteger<int32>required
    The rule's position: lower numbers are tried first.
  - querymap<string, object>required
    What the request must match: field paths (metadata.*, params.*) to operator objects, as described for the rule's request form.
  - then_target_namestringrequired
    The name of the target a matching request goes to.
  - idstring<uuid>
    The rule's id (UUID). Changes whenever the config's targets are replaced by an update.
- override_paramsobject
  Request parameters a routing target sets on the requests it receives, in place of the caller's. A field left out keeps the caller's value. model, temperature, max_tokens, top_p and stop are applied; the other fields are validated and stored but not applied at present.
  Child attributes
  - modelstring
    The model to call instead of the request's, e.g. gpt-4o-mini.
  - temperaturenumber<double>
    The sampling temperature, from 0 to 2.
  - max_tokensinteger<int32>
    The most tokens to generate; at least 1.
  - top_pnumber<double>
    Nucleus sampling, from 0 to 1.
  - frequency_penaltynumber<double>
    From -2 to 2. Stored, not applied at present.
  - presence_penaltynumber<double>
    From -2 to 2. Stored, not applied at present.
  - stopstring[]
    Stop sequences; a non-empty list replaces the request's.
  - seedinteger<int32>
    A sampling seed, at least 0. Stored, not applied at present.
  - response_format_typeenum<string>
    json_object, text or json_schema. Accepted, but neither applied nor returned at present.
    One of "json_object", "text", "json_schema"
- cacheobject
  Response cache settings stored with a routing config or target. Requests served through a routing config are not answered from the response cache at present.
  Child attributes
  - modestring
    The cache mode: simple (exact match) or semantic. Absent: none.
  - max_age_secondsinteger<int32>
    How long a cached answer stays valid, in seconds. Absent: none.
- retryobject
  Retries for a routing target's provider calls. A failed call with a listed status is tried again after 1, 2, 4, ... seconds (at most 16), until attempts calls have been made.
  Child attributes
  - attemptsinteger<int32>required
    How many calls to make in all, the first one included (1 means no retry). From 1 to 10. Required.
  - on_status_codesinteger<int32>[]
    The provider HTTP statuses to retry. Empty or absent: 429, 500, 502, 503 and 504.
- request_timeout_msinteger<int32>
  For a virtual key target: the time limit per provider call, in milliseconds. Absent: no limit of its own.
- idstring<uuid>
  The target's id (UUID). Changes whenever the config's targets are replaced by an update.
conditionsobject[]
For CONDITIONAL: the top-level rules, in condition_order. Empty otherwise.
Child attributes
- condition_orderinteger<int32>required
  The rule's position: lower numbers are tried first.
- querymap<string, object>required
  What the request must match: field paths (metadata.*, params.*) to operator objects, as described for the rule's request form.
- then_target_namestringrequired
  The name of the target a matching request goes to.
- idstring<uuid>
  The rule's id (UUID). Changes whenever the config's targets are replaced by an update.
cacheobject
Response cache settings stored with a routing config or target. Requests served through a routing config are not answered from the response cache at present.
Child attributes
- modestring
  The cache mode: simple (exact match) or semantic. Absent: none.
- max_age_secondsinteger<int32>
  How long a cached answer stays valid, in seconds. Absent: none.
retryobject
Retries for a routing target's provider calls. A failed call with a listed status is tried again after 1, 2, 4, ... seconds (at most 16), until attempts calls have been made.
Child attributes
- attemptsinteger<int32>required
  How many calls to make in all, the first one included (1 means no retry). From 1 to 10. Required.
- on_status_codesinteger<int32>[]
  The provider HTTP statuses to retry. Empty or absent: 429, 500, 502, 503 and 504.
request_timeout_msinteger<int32>
The stored time limit in milliseconds (applied only on virtual key targets). Absent when none was set.
schema_versioninteger<int32>
The version of the config format. Currently always 1.
created_bystring
Who created the config: an identifier of the user, or of the API key, that made the request.
created_atstring<date-time>
When the config was created (ISO 8601 date-time).
updated_atstring<date-time>
When the config last changed (ISO 8601 date-time).

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