Start a GRPO run

curl --request POST \
  --url https://gateway.omnia-voice.com/v1/grpo/runs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "reward": {
    "criterionId": "<string>",
    "criterionIds": [
      "<string>"
    ],
    "assertions": "<array>"
  },
  "model": "<string>",
  "promptCount": 2,
  "rewardBudgetUsd": 123,
  "gpuHourBudget": 123,
  "promptTag": "<string>",
  "groupSize": 123,
  "maxSteps": 123,
  "useCandidateQueue": true,
  "allowSideEffects": false,
  "useVllm": true,
  "vllmGpuMemoryUtilization": 123,
  "qlora": true,
  "paramsB": 123,
  "autoProvision": true,
  "curriculumMixRatio": 0.45,
  "holdoutCount": 123,
  "maxCompletionTokens": 123,
  "tasksInline": "<array>"
}
'

import requests

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

payload = {
    "reward": {
        "criterionId": "<string>",
        "criterionIds": ["<string>"],
        "assertions": "<array>"
    },
    "model": "<string>",
    "promptCount": 2,
    "rewardBudgetUsd": 123,
    "gpuHourBudget": 123,
    "promptTag": "<string>",
    "groupSize": 123,
    "maxSteps": 123,
    "useCandidateQueue": True,
    "allowSideEffects": False,
    "useVllm": True,
    "vllmGpuMemoryUtilization": 123,
    "qlora": True,
    "paramsB": 123,
    "autoProvision": True,
    "curriculumMixRatio": 0.45,
    "holdoutCount": 123,
    "maxCompletionTokens": 123,
    "tasksInline": "<array>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    reward: {criterionId: '<string>', criterionIds: ['<string>'], assertions: '<array>'},
    model: '<string>',
    promptCount: 2,
    rewardBudgetUsd: 123,
    gpuHourBudget: 123,
    promptTag: '<string>',
    groupSize: 123,
    maxSteps: 123,
    useCandidateQueue: true,
    allowSideEffects: false,
    useVllm: true,
    vllmGpuMemoryUtilization: 123,
    qlora: true,
    paramsB: 123,
    autoProvision: true,
    curriculumMixRatio: 0.45,
    holdoutCount: 123,
    maxCompletionTokens: 123,
    tasksInline: '<array>'
  })
};

fetch('https://gateway.omnia-voice.com/v1/grpo/runs', 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/grpo/runs",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'reward' => [
        'criterionId' => '<string>',
        'criterionIds' => [
                '<string>'
        ],
        'assertions' => '<array>'
    ],
    'model' => '<string>',
    'promptCount' => 2,
    'rewardBudgetUsd' => 123,
    'gpuHourBudget' => 123,
    'promptTag' => '<string>',
    'groupSize' => 123,
    'maxSteps' => 123,
    'useCandidateQueue' => true,
    'allowSideEffects' => false,
    'useVllm' => true,
    'vllmGpuMemoryUtilization' => 123,
    'qlora' => true,
    'paramsB' => 123,
    'autoProvision' => true,
    'curriculumMixRatio' => 0.45,
    'holdoutCount' => 123,
    'maxCompletionTokens' => 123,
    'tasksInline' => '<array>'
  ]),
  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/grpo/runs"

	payload := strings.NewReader("{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}")

	req, _ := http.NewRequest("POST", 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.post("https://gateway.omnia-voice.com/v1/grpo/runs")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}"

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

{
  "trigger_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": "Insufficient balance: deploying this endpoint requires at least 1h of runway. Top up and try again.",
    "type": "insufficient_quota",
    "code": "insufficient_balance"
  }
}

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

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

POST

grpo

runs

Start a GRPO run

curl --request POST \
  --url https://gateway.omnia-voice.com/v1/grpo/runs \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "reward": {
    "criterionId": "<string>",
    "criterionIds": [
      "<string>"
    ],
    "assertions": "<array>"
  },
  "model": "<string>",
  "promptCount": 2,
  "rewardBudgetUsd": 123,
  "gpuHourBudget": 123,
  "promptTag": "<string>",
  "groupSize": 123,
  "maxSteps": 123,
  "useCandidateQueue": true,
  "allowSideEffects": false,
  "useVllm": true,
  "vllmGpuMemoryUtilization": 123,
  "qlora": true,
  "paramsB": 123,
  "autoProvision": true,
  "curriculumMixRatio": 0.45,
  "holdoutCount": 123,
  "maxCompletionTokens": 123,
  "tasksInline": "<array>"
}
'

import requests

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

payload = {
    "reward": {
        "criterionId": "<string>",
        "criterionIds": ["<string>"],
        "assertions": "<array>"
    },
    "model": "<string>",
    "promptCount": 2,
    "rewardBudgetUsd": 123,
    "gpuHourBudget": 123,
    "promptTag": "<string>",
    "groupSize": 123,
    "maxSteps": 123,
    "useCandidateQueue": True,
    "allowSideEffects": False,
    "useVllm": True,
    "vllmGpuMemoryUtilization": 123,
    "qlora": True,
    "paramsB": 123,
    "autoProvision": True,
    "curriculumMixRatio": 0.45,
    "holdoutCount": 123,
    "maxCompletionTokens": 123,
    "tasksInline": "<array>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    reward: {criterionId: '<string>', criterionIds: ['<string>'], assertions: '<array>'},
    model: '<string>',
    promptCount: 2,
    rewardBudgetUsd: 123,
    gpuHourBudget: 123,
    promptTag: '<string>',
    groupSize: 123,
    maxSteps: 123,
    useCandidateQueue: true,
    allowSideEffects: false,
    useVllm: true,
    vllmGpuMemoryUtilization: 123,
    qlora: true,
    paramsB: 123,
    autoProvision: true,
    curriculumMixRatio: 0.45,
    holdoutCount: 123,
    maxCompletionTokens: 123,
    tasksInline: '<array>'
  })
};

fetch('https://gateway.omnia-voice.com/v1/grpo/runs', 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/grpo/runs",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'reward' => [
        'criterionId' => '<string>',
        'criterionIds' => [
                '<string>'
        ],
        'assertions' => '<array>'
    ],
    'model' => '<string>',
    'promptCount' => 2,
    'rewardBudgetUsd' => 123,
    'gpuHourBudget' => 123,
    'promptTag' => '<string>',
    'groupSize' => 123,
    'maxSteps' => 123,
    'useCandidateQueue' => true,
    'allowSideEffects' => false,
    'useVllm' => true,
    'vllmGpuMemoryUtilization' => 123,
    'qlora' => true,
    'paramsB' => 123,
    'autoProvision' => true,
    'curriculumMixRatio' => 0.45,
    'holdoutCount' => 123,
    'maxCompletionTokens' => 123,
    'tasksInline' => '<array>'
  ]),
  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/grpo/runs"

	payload := strings.NewReader("{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}")

	req, _ := http.NewRequest("POST", 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.post("https://gateway.omnia-voice.com/v1/grpo/runs")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"reward\": {\n    \"criterionId\": \"<string>\",\n    \"criterionIds\": [\n      \"<string>\"\n    ],\n    \"assertions\": \"<array>\"\n  },\n  \"model\": \"<string>\",\n  \"promptCount\": 2,\n  \"rewardBudgetUsd\": 123,\n  \"gpuHourBudget\": 123,\n  \"promptTag\": \"<string>\",\n  \"groupSize\": 123,\n  \"maxSteps\": 123,\n  \"useCandidateQueue\": true,\n  \"allowSideEffects\": false,\n  \"useVllm\": true,\n  \"vllmGpuMemoryUtilization\": 123,\n  \"qlora\": true,\n  \"paramsB\": 123,\n  \"autoProvision\": true,\n  \"curriculumMixRatio\": 0.45,\n  \"holdoutCount\": 123,\n  \"maxCompletionTokens\": 123,\n  \"tasksInline\": \"<array>\"\n}"

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

{
  "trigger_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": "Insufficient balance: deploying this endpoint requires at least 1h of runway. Top up and try again.",
    "type": "insufficient_quota",
    "code": "insufficient_balance"
  }
}

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

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

Authorizations

Authorization

string

header

required

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

Body

application/json

This body is camelCase (promptCount, rewardBudgetUsd), unlike the snake_case loop endpoints. Types and presence are validated at the route; numeric bounds live in the shared service, the same source of truth the dashboard uses.

reward

object

required

The validated reward. Agentic runs (environment set) require a trace-unit aligned criterion.

Show child attributes

model

string

required

The base model to train.

promptCount

integer

required

How many logged prompts feed the run.

Required range: x >= 1

rewardBudgetUsd

number

required

Hard ceiling on judge/reward spend. The reward server refuses scoring calls past it (ledger-true kill switch).

gpuHourBudget

number

required

Wall-clock GPU budget, enforced by the orchestrator.

promptTag

string

Sample training prompts from traffic with this tag.

groupSize

integer

Completions sampled per prompt per step (the G in GRPO).

maxSteps

integer

useCandidateQueue

boolean

Train on the workspace's GRPO-candidate queue (prompts offline RAFT gave up on) instead of a tag sample.

platformGpu

object

Platform-provisioned GPU: rate and markup are frozen at start and billed hourly while ACTIVE. Omit for a BYO-GPU run (no GPU billing).

Show child attributes

allowSideEffects

boolean

default:false

Agentic runs: permit calls to tools not declared read-only. Default false.

environment

object

Agentic mode: run episodes against the declared tool environment (see /v1/env/tools).

Show child attributes

useVllm

boolean

vLLM colocated rollouts. Forced on for agentic runs.

vllmGpuMemoryUtilization

number

qlora

boolean

default:true

QLoRA 4-bit training.

paramsB

number

Parameter-count override for models whose name doesn't carry it.

autoProvision

boolean

The platform provisions the GPU box (auto-sized). Refused when platform provisioning isn't configured.

curriculumMixRatio

number

Candidate-queue runs: fraction of the training slice drawn from regular successful traffic.

Required range: 0 <= x <= 0.9

holdoutCount

integer

Holdout size for the bake-off; use 50+ for a real claim.

maxCompletionTokens

integer

Per-rollout generated-token budget. Agentic default 8192; single-turn 1024.

tasksInline

array

Task objects: {goal, image?, recorded?, verifier?: [{command, timeout_sec}]}. Max 10000. The unit of agentic work; benchmark suites import here.

Maximum array length: 10000

autoAdopt

object

Opt-in per run: an "improved" bake-off verdict triggers deploy, then a canary on this alias under the online gate.

Show child attributes

Response

Started. The run id appears in GET /v1/grpo/runs.

trigger_run_id

string

Internal orchestration handle.

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

Start a GRPO run

Authorizations

Body

Response