curl --request POST \
  --url https://api.together.ai/v1/rl/model-resources \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "base_model": "Qwen/Qwen3.5-4B",
  "base_weights_ref": "together://ml_A1b2C3d4E5f6G7h8I9j0K",
  "compute_config": {
    "num_generator_replicas": 2,
    "gpu_type": "B200-SXM"
  },
  "lora_enabled": true,
  "optimizer_config": {
    "adam": {},
    "muon": {
      "scaling_strategy": "MUON_SCALING_STRATEGY_ORIGINAL"
    }
  }
}
'

import requests

url = "https://api.together.ai/v1/rl/model-resources"

payload = {
    "base_model": "Qwen/Qwen3.5-4B",
    "base_weights_ref": "together://ml_A1b2C3d4E5f6G7h8I9j0K",
    "compute_config": {
        "num_generator_replicas": 2,
        "gpu_type": "B200-SXM"
    },
    "lora_enabled": True,
    "optimizer_config": {
        "adam": {},
        "muon": { "scaling_strategy": "MUON_SCALING_STRATEGY_ORIGINAL" }
    }
}
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({
    base_model: 'Qwen/Qwen3.5-4B',
    base_weights_ref: 'together://ml_A1b2C3d4E5f6G7h8I9j0K',
    compute_config: {num_generator_replicas: 2, gpu_type: 'B200-SXM'},
    lora_enabled: true,
    optimizer_config: {adam: {}, muon: {scaling_strategy: 'MUON_SCALING_STRATEGY_ORIGINAL'}}
  })
};

fetch('https://api.together.ai/v1/rl/model-resources', 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://api.together.ai/v1/rl/model-resources",
  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([
    'base_model' => 'Qwen/Qwen3.5-4B',
    'base_weights_ref' => 'together://ml_A1b2C3d4E5f6G7h8I9j0K',
    'compute_config' => [
        'num_generator_replicas' => 2,
        'gpu_type' => 'B200-SXM'
    ],
    'lora_enabled' => true,
    'optimizer_config' => [
        'adam' => [
                
        ],
        'muon' => [
                'scaling_strategy' => 'MUON_SCALING_STRATEGY_ORIGINAL'
        ]
    ]
  ]),
  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://api.together.ai/v1/rl/model-resources"

	payload := strings.NewReader("{\n  \"base_model\": \"Qwen/Qwen3.5-4B\",\n  \"base_weights_ref\": \"together://ml_A1b2C3d4E5f6G7h8I9j0K\",\n  \"compute_config\": {\n    \"num_generator_replicas\": 2,\n    \"gpu_type\": \"B200-SXM\"\n  },\n  \"lora_enabled\": true,\n  \"optimizer_config\": {\n    \"adam\": {},\n    \"muon\": {\n      \"scaling_strategy\": \"MUON_SCALING_STRATEGY_ORIGINAL\"\n    }\n  }\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://api.together.ai/v1/rl/model-resources")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"base_model\": \"Qwen/Qwen3.5-4B\",\n  \"base_weights_ref\": \"together://ml_A1b2C3d4E5f6G7h8I9j0K\",\n  \"compute_config\": {\n    \"num_generator_replicas\": 2,\n    \"gpu_type\": \"B200-SXM\"\n  },\n  \"lora_enabled\": true,\n  \"optimizer_config\": {\n    \"adam\": {},\n    \"muon\": {\n      \"scaling_strategy\": \"MUON_SCALING_STRATEGY_ORIGINAL\"\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.together.ai/v1/rl/model-resources")

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  \"base_model\": \"Qwen/Qwen3.5-4B\",\n  \"base_weights_ref\": \"together://ml_A1b2C3d4E5f6G7h8I9j0K\",\n  \"compute_config\": {\n    \"num_generator_replicas\": 2,\n    \"gpu_type\": \"B200-SXM\"\n  },\n  \"lora_enabled\": true,\n  \"optimizer_config\": {\n    \"adam\": {},\n    \"muon\": {\n      \"scaling_strategy\": \"MUON_SCALING_STRATEGY_ORIGINAL\"\n    }\n  }\n}"

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

{
  "id": "123e4567-e89b-12d3-a456-426614174000",
  "status": "MODEL_RESOURCES_STATUS_READY",
  "base_model": "Qwen/Qwen3.5-4B",
  "compute_config": {
    "num_generator_replicas": 1,
    "gpu_type": "H100-80GB"
  },
  "lora_enabled": true,
  "created_at": "2026-01-02T00:00:00Z",
  "updated_at": "2026-01-02T00:00:05Z",
  "optimizer_config": {
    "adam": {},
    "muon": {
      "scaling_strategy": "MUON_SCALING_STRATEGY_ORIGINAL"
    }
  },
  "created_by": "user_123",
  "error": {
    "code": "MODEL_RESOURCES_ERROR_CODE_CAPACITY_WAIT_TIMEOUT",
    "message": "Timed out waiting for cluster capacity. Try again later.",
    "occurred_at": "2026-01-02T00:00:05Z"
  },
  "base_weights_ref": "together://ml_A1b2C3d4E5f6G7h8I9j0K@rv_A1b2C3d4E5f6G7h8I9j0K"
}

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

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