Create or repoint an alias

curl --request PUT \
  --url https://gateway.omnia-voice.com/v1/aliases \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "support-bot",
  "target_model": "Qwen/Qwen3-32B",
  "canary_model": "<string>",
  "canary_percent": 0,
  "description": "switched after eval ev_123 (90% win, -88% cost)",
  "gate_criterion_id": "<string>",
  "gate_mode": "recommend",
  "gate_min_samples": 50,
  "gate_rollback_threshold": 0.7,
  "gate_window_hours": 168,
  "require_evidence": true,
  "override_reason": "<string>"
}
'

import requests

url = "https://gateway.omnia-voice.com/v1/aliases"

payload = {
    "name": "support-bot",
    "target_model": "Qwen/Qwen3-32B",
    "canary_model": "<string>",
    "canary_percent": 0,
    "description": "switched after eval ev_123 (90% win, -88% cost)",
    "gate_criterion_id": "<string>",
    "gate_mode": "recommend",
    "gate_min_samples": 50,
    "gate_rollback_threshold": 0.7,
    "gate_window_hours": 168,
    "require_evidence": True,
    "override_reason": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.put(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PUT',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'support-bot',
    target_model: 'Qwen/Qwen3-32B',
    canary_model: '<string>',
    canary_percent: 0,
    description: 'switched after eval ev_123 (90% win, -88% cost)',
    gate_criterion_id: '<string>',
    gate_mode: 'recommend',
    gate_min_samples: 50,
    gate_rollback_threshold: 0.7,
    gate_window_hours: 168,
    require_evidence: true,
    override_reason: '<string>'
  })
};

fetch('https://gateway.omnia-voice.com/v1/aliases', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://gateway.omnia-voice.com/v1/aliases",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PUT",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => 'support-bot',
    'target_model' => 'Qwen/Qwen3-32B',
    'canary_model' => '<string>',
    'canary_percent' => 0,
    'description' => 'switched after eval ev_123 (90% win, -88% cost)',
    'gate_criterion_id' => '<string>',
    'gate_mode' => 'recommend',
    'gate_min_samples' => 50,
    'gate_rollback_threshold' => 0.7,
    'gate_window_hours' => 168,
    'require_evidence' => true,
    'override_reason' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://gateway.omnia-voice.com/v1/aliases"

	payload := strings.NewReader("{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}")

	req, _ := http.NewRequest("PUT", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.put("https://gateway.omnia-voice.com/v1/aliases")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://gateway.omnia-voice.com/v1/aliases")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Put.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "name": "support-bot",
  "target_model": "<string>",
  "canary_model": "<string>",
  "canary_percent": 123,
  "description": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "gate_criterion_id": "<string>",
  "gate_mode": "recommend",
  "gate_verdict": {},
  "gate_verdict_at": "2023-11-07T05:31:56Z",
  "gate_min_samples": 123,
  "gate_rollback_threshold": 123,
  "gate_window_hours": 123,
  "model_version_id": "<string>",
  "require_evidence": true,
  "last_evidence_run_id": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "Invalid API key",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

Model aliases API

Create or repoint an alias

Point a stable name at a model — and repoint it whenever you like, with no change to your code.

Your application keeps calling support-bot; the next request after a repoint already routes to the new model. This is what makes an eval result actionable: prove a cheaper model holds up, then repoint.

Upsert by name, so CI can repoint idempotently without a lookup first. Owner/admin key required — repointing silently redirects live production traffic, so it’s audited with the before/after.

You are always billed for the model that RAN. An alias is a routing decision, never a pricing one.

PUT

aliases

Create or repoint an alias

curl --request PUT \
  --url https://gateway.omnia-voice.com/v1/aliases \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "support-bot",
  "target_model": "Qwen/Qwen3-32B",
  "canary_model": "<string>",
  "canary_percent": 0,
  "description": "switched after eval ev_123 (90% win, -88% cost)",
  "gate_criterion_id": "<string>",
  "gate_mode": "recommend",
  "gate_min_samples": 50,
  "gate_rollback_threshold": 0.7,
  "gate_window_hours": 168,
  "require_evidence": true,
  "override_reason": "<string>"
}
'

import requests

url = "https://gateway.omnia-voice.com/v1/aliases"

payload = {
    "name": "support-bot",
    "target_model": "Qwen/Qwen3-32B",
    "canary_model": "<string>",
    "canary_percent": 0,
    "description": "switched after eval ev_123 (90% win, -88% cost)",
    "gate_criterion_id": "<string>",
    "gate_mode": "recommend",
    "gate_min_samples": 50,
    "gate_rollback_threshold": 0.7,
    "gate_window_hours": 168,
    "require_evidence": True,
    "override_reason": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.put(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PUT',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'support-bot',
    target_model: 'Qwen/Qwen3-32B',
    canary_model: '<string>',
    canary_percent: 0,
    description: 'switched after eval ev_123 (90% win, -88% cost)',
    gate_criterion_id: '<string>',
    gate_mode: 'recommend',
    gate_min_samples: 50,
    gate_rollback_threshold: 0.7,
    gate_window_hours: 168,
    require_evidence: true,
    override_reason: '<string>'
  })
};

fetch('https://gateway.omnia-voice.com/v1/aliases', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://gateway.omnia-voice.com/v1/aliases",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PUT",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => 'support-bot',
    'target_model' => 'Qwen/Qwen3-32B',
    'canary_model' => '<string>',
    'canary_percent' => 0,
    'description' => 'switched after eval ev_123 (90% win, -88% cost)',
    'gate_criterion_id' => '<string>',
    'gate_mode' => 'recommend',
    'gate_min_samples' => 50,
    'gate_rollback_threshold' => 0.7,
    'gate_window_hours' => 168,
    'require_evidence' => true,
    'override_reason' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://gateway.omnia-voice.com/v1/aliases"

	payload := strings.NewReader("{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}")

	req, _ := http.NewRequest("PUT", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.put("https://gateway.omnia-voice.com/v1/aliases")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://gateway.omnia-voice.com/v1/aliases")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Put.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"support-bot\",\n  \"target_model\": \"Qwen/Qwen3-32B\",\n  \"canary_model\": \"<string>\",\n  \"canary_percent\": 0,\n  \"description\": \"switched after eval ev_123 (90% win, -88% cost)\",\n  \"gate_criterion_id\": \"<string>\",\n  \"gate_mode\": \"recommend\",\n  \"gate_min_samples\": 50,\n  \"gate_rollback_threshold\": 0.7,\n  \"gate_window_hours\": 168,\n  \"require_evidence\": true,\n  \"override_reason\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "id": "<string>",
  "name": "support-bot",
  "target_model": "<string>",
  "canary_model": "<string>",
  "canary_percent": 123,
  "description": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "gate_criterion_id": "<string>",
  "gate_mode": "recommend",
  "gate_verdict": {},
  "gate_verdict_at": "2023-11-07T05:31:56Z",
  "gate_min_samples": 123,
  "gate_rollback_threshold": 123,
  "gate_window_hours": 123,
  "model_version_id": "<string>",
  "require_evidence": true,
  "last_evidence_run_id": "<string>"
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "Invalid API key",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "code": "<string>"
  }
}

Authorizations

Authorization

string

header

required

Your workspace API key, e.g. sk_sovereign_..., sent as Authorization: Bearer <key>.

Body

application/json

name

string

required

3–64 chars (letters, numbers, dots, dashes, underscores). Scoped to your workspace — a name that isn't an alias is treated as a normal model id, so aliases never shadow the catalog.

Example:

"support-bot"

target_model

string

required

The model requests route to. Validated against the live catalog.

Example:

"Qwen/Qwen3-32B"

canary_model

string | null

Optional. A share of requests route here instead — for a gradual cutover.

canary_percent

integer

default:0

0 = no split. 100 = full cutover. The split is per REQUEST, not per user.

Required range: 0 <= x <= 100

description

string | null

Maximum string length: 200

Example:

"switched after eval ev_123 (90% win, -88% cost)"

gate_criterion_id

string | null

Turn the canary split into a supervised rollout: the online scorer judges BOTH arms with this criterion and the gate decides on corrected-rate CI bounds. The criterion must have been aligned against your labels.

gate_mode

enum<string>

default:recommend

recommend: verdicts surface on GET /v1/aliases (gate_verdict) and via alert notifications — you click the button. auto: the gate may repoint the alias itself (promote) or zero the canary (roll back), always audited with the numbers. Auto requires an ALIGNED criterion (TPR and TNR ≥ 90%): a judge may recommend with a weaker signal, but it doesn't get the keys.

Available options:

recommend,

auto

gate_min_samples

integer

default:50

No verdict of any kind until BOTH arms have this many scored requests.

Required range: 10 <= x <= 1000

gate_rollback_threshold

number

default:0.7

Roll back only when even the canary's OPTIMISTIC bound (CI upper) sits below this — confidently bad, not unluckily sampled.

Required range: 0 <= x <= 1

gate_window_hours

integer

default:168

Scores older than this don't count toward the verdict.

Required range: 1 <= x <= 720

require_evidence

boolean

Omitted = leave the alias's existing policy alone (a plain repoint can't quietly switch the policy off); false on create. With it on, a PUT that routes traffic to a model it isn't already reaching must be backed by a finished comparison in this workspace, within the last 30 days, whose candidate win-rate CI lower bound clears 50% against the model traffic is leaving. Refusals are 412.

override_reason

string | null

The audited escape hatch for an evidence refusal: a written justification of at least 10 characters lets the repoint through and writes an audit event naming the actor, both models, and the reason. Omitted or blank is not an override.

Response

The alias.

string

name

string

The name you put in model.

Example:

"support-bot"

target_model

string

The model this resolves to today.

canary_model

string | null

canary_percent

integer

0–100. Share of requests routed to canaryModel.

description

string | null

created_at

string<date-time>

updated_at

string<date-time>

gate_criterion_id

string | null

gate_mode

enum<string>

Available options:

recommend,

auto

gate_verdict

object | null

The last gate evaluation: {decision: promote|rollback|hold, reason, canary: {model, rate, ci, judged}, incumbent: {...}, acted}.

gate_verdict_at

string<date-time> | null

gate_min_samples

integer

No gate verdict until both canary arms have this many scored samples in the window.

gate_rollback_threshold

number

Roll back only when even the canary's optimistic bound (CI upper) sits below this corrected pass rate.

gate_window_hours

integer

Scores older than this do not count toward the verdict.

model_version_id

string | null

The model version this alias currently serves, when it points at a trained version (null for raw catalog models). Repoint to an older version to roll back.

require_evidence

boolean

Evidence policy: with this on, a repoint that would send traffic to an unproven model is refused with 412 unless a passing, in-window comparison exists (or an audited override_reason is given).

last_evidence_run_id

string | null

The eval run that authorized the current routing. Null when the routing predates the policy or went through as an audited override.

Overview

Inference API

Capture & setup API

Logs & datasets API

Grades (labels) API

Judges (criteria) API

Evals API

Fine-tuning API

Reinforcement learning API

Dedicated endpoints API

Model aliases API

Model versions API

Create or repoint an alias

Authorizations

Body

Response