Authentication

The Helyx API uses API keys for authentication. You can obtain your free API key from your dashboard. Authentication is performed via the standard HTTP Authorization header.

Authorization: Bearer YOUR_API_KEY

Keep your keys secure. Do not expose your API keys in client-side code (like browser-facing JavaScript). Always route requests through your own backend.

Base URL

All API requests must be routed to our universal v1 endpoint. If you are using an official OpenAI SDK, simply override the base URL.

BASE_URL = "https://helyxai.space/v1"

Chat Completions POST /v1/chat/completions

Used for text-based models like Llama 4, Mistral, Qwen, and DeepSeek. Generates a model response for the given chat conversation.

from openai import OpenAI

client = OpenAI(
    base_url="https://helyxai.space/v1",
    api_key="sk-your-api-key"
)

response = client.chat.completions.create(
    model="gpt-oss-120b", # Swap this string for any text model
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing."}
    ]
)

print(response.choices[0].message.content)

curl https://helyxai.space/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Explain quantum computing."
      }
    ]
  }'

const response = await fetch('https://helyxai.space/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-your-api-key'
  },
  body: JSON.stringify({
    "model": "gpt-oss-120b",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Explain quantum computing." }
    ]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Image Generation POST /v1/images/generations

Creates an image given a prompt. Fully compatible with the standard OpenAI images SDK. Use models like `flux-1`.

from openai import OpenAI

client = OpenAI(
    base_url="https://helyxai.space/v1",
    api_key="sk-your-api-key"
)

response = client.images.generate(
    model="flux-1",
    prompt="A cinematic shot of a futuristic cyberpunk city at night, 4k",
    size="1024x1024",
    n=1
)

print(response.data[0].url)

curl https://helyxai.space/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "flux-1",
    "prompt": "A cinematic shot of a futuristic cyberpunk city at night, 4k",
    "size": "1024x1024",
    "n": 1
  }'

const response = await fetch('https://helyxai.space/v1/images/generations', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-your-api-key'
  },
  body: JSON.stringify({
    "model": "flux-1",
    "prompt": "A cinematic shot of a futuristic cyberpunk city at night, 4k",
    "size": "1024x1024",
    "n": 1
  })
});

const data = await response.json();
console.log(data.data[0].url);

Video Generation POST /v1/videos/generations

Because the official OpenAI SDK does not yet natively support a `videos` module, you can easily call this endpoint using standard HTTP requests.

import requests

url = "https://helyxai.space/v1/videos/generations"
headers = {
    "Authorization": "Bearer sk-your-api-key",
    "Content-Type": "application/json"
}
data = {
    "model": "kling-video",
    "prompt": "A golden retriever flying on a skateboard through clouds",
    "duration": 5 # seconds
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(result['data'][0]['url'])

curl https://helyxai.space/v1/videos/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "kling-video",
    "prompt": "A golden retriever flying on a skateboard through clouds",
    "duration": 5
  }'

const response = await fetch('https://helyxai.space/v1/videos/generations', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-your-api-key'
  },
  body: JSON.stringify({
    "model": "kling-video",
    "prompt": "A golden retriever flying on a skateboard through clouds",
    "duration": 5
  })
});

const data = await response.json();
console.log(data.data[0].url);

Streaming Responses (SSE)

For faster perceived response times in UI applications, set `stream=True` in your chat completion requests. Helyx fully supports Server-Sent Events (SSE). When streaming, token usage is automatically appended to the final `[DONE]` chunk to ensure accurate billing and limit tracking.

response = client.chat.completions.create(..., stream=True)

Errors & Rate Limits

The Free plan grants 100,000 tokens daily, resetting every 24 hours. Media generation (Images/Video) is converted into equivalent token costs dynamically based on the model's pricing.

Status Code	Error Type	Description
401	invalid_api_key	API key is missing, inactive, or incorrect.
403	insufficient_quota	Your account tier does not have access to this specific model.
429	rate_limit_exceeded	You have exhausted your 100k daily free token limit. Resets at midnight.
500	server_error	The upstream provider failed to process the request.

Contact Support

API Documentation