← Home
Docs • Services Pro

Services Pro Documentation

API documentation for AI text generation. Includes base URL, authentication, request format, and code examples for Python and JavaScript.

Service Links

Base URL
https://services-pro.ryzenths.dpdns.org
Optional
Userbot-Auth Free Rate Limit

Quick Navigation

Rate • Limits

API requests are rate-limited per API key and scope to keep the service stable for all users. When limits are exceeded, the API returns 429.

Trial keys fw_trial_xxx
  • 30 requests per 60 seconds
  • Text scope only
Pro keys fw_live_xxx
  • 60 requests per 120 seconds
  • Scope depends on selected plan
Rate limit response
{
 "error": "rate_limit",
 "code": "RATE_LIMITED"
}

Limits may change during maintenance or high traffic periods.

Endpoint:POST/api/text/generate
Authentication:x-api-key
Full endpoint URL
https://services-pro.ryzenths.dpdns.org/api/text/generate

Text • API

Text using a secured API endpoint.

Limited Trial Access
Endpoint:POST/api/text/generate
Authentication:x-api-key
Full code
import requests

payload = {
    "messages": [{"role": "user", "content": "Hello world"}]
}

resp = requests.post(
    "https://services-pro.ryzenths.dpdns.org/api/text/generate",
    json=payload,
    headers={"x-api-key": "fw_live_xxxxx"}
)

print(resp.json())

Chat Completions • API

Chat Completions using a secured API endpoint.

Pro Access Required
Endpoint:POST/api/v1/chat/completions
Authentication:x-api-key
Full code
import OpenAI from 'openai';

/*
// List Models
omni-visio-pro
cortex-view-7b
deepcoder-14b-preview
quantum-script-pro
synapse-code-ultra
byte-forge-32b
nexus-chat-ultra
aura-talk-pro
quantum-dialogue-8b
synapse-chat-lite
dolphin-mistral-24b-venice-edition
hermes-reason-8b
logic-core-ultra
inferix-reason-pro
flash-think-2.0
quantum-pulse-3b
neura-stream-24b
velocity-core-9b
maverick-4-pro
scout-4-lite
quantum-nexus-32b
infinity-core-235b
reka-flash-3-turbo
hunyuan-chat-pro
glm-air-4.5-plus
sarvam-m-ultra
chimera-r1t-ultra
chimera-r1t2-pro
kimi-dev-72b-plus
kimi-vision-alpha
gemma-nano-3b
gemma-micro-9b
gemma-macro-27b
neura-mini-3n
gpt-oss-20b-pro
shisa-v2-ultra
nemotron-ultra-253b
microsoft-mai-ds-r1-pro
devstral-small-2505-pro
mistral-nemo-plus
*/

const clients = new OpenAI({
  apiKey: "fw_live_xxx",
  baseURL: "https://services-pro.ryzenths.dpdns.org/api/v1"
});

const completion = await clients.chat.completions.create({
  model: 'gpt-oss-20b-pro',
  messages: [
    { role: 'system', content: 'Talk like a pirate.' },
    { role: 'user', content: "What's your name?" },
  ],
});

console.log(completion.choices[0].message.content);
Output
{
    "id": "chatcmpl-1770146740332-ggw2g6fgv",
    "model": "gpt-oss-20b-pro",
    "object": "chat.completion",
    "created": 1770146739,
    "choices": [
        {
            "logprobs": null,
            "finish_reason": "stop",
            "native_finish_reason": "stop",
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "You’re welcome! If you have any more questions or need further assistance, just let me know. Have a great day!",
                "refusal": null,
                "reasoning": "The user says "ok thanks". They likely want a response acknowledging. Probably a friendly closing.",
                "reasoning_details": [
                    {
                        "format": "unknown",
                        "index": 0,
                        "type": "reasoning.text",
                        "text": "The user says "ok thanks". They likely want a response acknowledging. Probably a friendly closing."
                    }
                ]
            }
        }
    ],
    "usage": {
        "prompt_tokens": 71,
        "completion_tokens": 54,
        "total_tokens": 125,
        "cost": 0,
        "is_byok": false,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "audio_tokens": 0
        },
        "cost_details": {
            "upstream_inference_cost": 0,
            "upstream_inference_prompt_cost": 0,
            "upstream_inference_completions_cost": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 25,
            "audio_tokens": 0
        }
    },
    "ryzenth_metadata": {
        "generated_at": "2026-02-03T19:25:40.332Z",
        "website": "services-pro.ryzenths.dpdns.org",
        "author": "Ryzenths",
        "original_model": "gpt-oss-20b-pro"
    }
}

Image • API

Image using a secured API endpoint.

Plus Access
Endpoint:POST/api/image/generate
Authentication:x-api-key
Full code
import requests

resp = requests.post(
    "https://services-pro.ryzenths.dpdns.org/api/image/generate",
    json={"input": "Make a picture of a cat"},
    headers={"x-api-key": "fw_live_xxxxx"}
)

print(resp.json())

Tiktok • API

Tiktok using a secured API endpoint.

Plus Access
Endpoint:POST/api/download/tiktok
Authentication:x-api-key
Full code
import requests

resp = requests.post(
    "https://services-pro.ryzenths.dpdns.org/api/download/tiktok",
    json={"url": "https://vt.tiktok.com/ZSMdyXqXd/"},
    headers={"x-api-key": "fw_live_xxxxx"}
)

print(resp.json())

Platform • API

Platform using a secured API endpoint.

Plus Access
Endpoint:POST/api/download/platform
Authentication:x-api-key
Full code
import requests

# platform: tiktok, facebook, instagram

resp = requests.post(
    "https://services-pro.ryzenths.dpdns.org/api/download/platform",
    json={"url": "", "platform": "tiktok"},
    headers={"x-api-key": "fw_live_xxxxx"}
)

print(resp.json())

Search • API

Search using a secured API endpoint.

Plus Access
Endpoint:POST/api/search
Authentication:x-api-key
Full code
import requests

resp = requests.post(
    "https://services-pro.ryzenths.dpdns.org/api/search",
    json={"query": "", "include_answer": "basic"},
    headers={"x-api-key": "fw_live_xxxxx"}
)

print(resp.json())
Still here? Start when you're ready.
PricingStart Trial