Getting Started

Get up and running with the Melious API in under 5 minutes. This guide shows you how to make your first API call using the OpenAI SDK or direct HTTP requests.

Prerequisites

A Melious account (sign up free)
An API key from melious.ai/account/api/keys

Quick Start

Create Your API Key

Go to melious.ai/account/api/keys
Click Create API Key
Give it a name (e.g., "Development")
Copy the key immediately - it's only shown once!

Store your API key securely. Never commit it to version control or expose it in client-side code.

Install the OpenAI SDK (Optional)

Melious is fully compatible with the official OpenAI SDK:

pip install openai

Make Your First Request

from openai import OpenAI

client = OpenAI(
    api_key="sk-mel-your-api-key-here",
    base_url="https://api.melious.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Say hello!"}]
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-mel-your-api-key-here',
  baseURL: 'https://api.melious.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'gpt-oss-120b',
  messages: [{ role: 'user', content: 'Say hello!' }]
});

console.log(response.choices[0].message.content);

curl https://api.melious.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-mel-your-api-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Say hello!"}]
  }'

Expected Response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699999999,
  "model": "gpt-oss-120b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 8,
    "total_tokens": 18
  }
}

Available Models

Melious provides access to 40+ open-source models from leading AI research labs:

Brand	Popular Models
OpenAI (OSS)	`gpt-oss-120b`, `gpt-oss-20b`
Qwen	`qwen3-235b-a22b-instruct`, `qwen3-coder-480b-a35b-instruct`
Moonshot	`kimi-k2-instruct`, `kimi-k2-thinking`
DeepSeek	`deepseek-r1-0528`
Mistral	`mistral-small-3.2-24b-instruct`, `devstral-small-2505`
Google	`gemma-3-27b`
Meta	`llama-3.3-70b-instruct`, `llama-3.1-8b-instruct`
NousResearch	`hermes-4-405b`, `hermes-4-70b`

# List all models
curl https://api.melious.ai/v1/models \
  -H "Authorization: Bearer sk-mel-your-api-key-here"

Privacy-first: All models are open-source and self-hosted on European infrastructure. Your data is never sent to OpenAI, Anthropic, or Google.

Try Different Features

Chat with Vision

Send images along with text for visual understanding.

Function Calling

Let models call your functions and tools.

Streaming

Get real-time responses as they're generated.

Embeddings

Generate vector embeddings for search and RAG.

Streaming Responses

Get responses in real-time:

stream = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Vision: Analyze Images

Send images for visual understanding (with vision-capable models):

response = client.chat.completions.create(
    model="mistral-small-3.2-24b-instruct",  # Vision-capable model
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
            ]
        }
    ]
)

Vision-capable models: mistral-small-3.2-24b-instruct, mistral-small-3.2-24b-instruct

Environment Variables

For production applications:

# .env file
MELIOUS_API_KEY=sk-mel-your-api-key-here

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MELIOUS_API_KEY"),
    base_url="https://api.melious.ai/v1"
)

Error Handling

from openai import OpenAI, APIError, RateLimitError, AuthenticationError

client = OpenAI(
    api_key="sk-mel-your-api-key-here",
    base_url="https://api.melious.ai/v1"
)

try:
    response = client.chat.completions.create(
        model="gpt-oss-120b",
        messages=[{"role": "user", "content": "Hello!"}]
    )
except AuthenticationError:
    print("Invalid API key")
except RateLimitError:
    print("Rate limited - wait and retry")
except APIError as e:
    print(f"API error: {e}")

Next Steps

Chat Completions

Full guide with all parameters.

Available Models

Explore 40+ available models.

AI Tools

Web search, URL scraping, and more.

Migrate from OpenAI

Already using OpenAI? Migration is simple:

# Before (OpenAI)
from openai import OpenAI
client = OpenAI(api_key="sk-...")

# After (Melious) - just add base_url!
from openai import OpenAI
client = OpenAI(
    api_key="sk-mel-...",
    base_url="https://api.melious.ai/v1"
)

# Your existing code works unchanged!
# Note: Use open-source model names (e.g., gpt-oss-120b instead of gpt-4o)

When migrating, replace model names with Melious equivalents:

gpt-4o → gpt-oss-120b or qwen3-235b-a22b-instruct
gpt-4o-mini → llama-3.1-8b-instruct or qwen3-32b
text-embedding-3-small → bge-m3 or qwen3-embedding-8b

Get Help

API Keys: melious.ai/account/api/keys
Settings: melious.ai/account/settings/data
Email: support@melious.ai

Getting Started

Chat with Vision

Function Calling

Streaming

Embeddings

Chat Completions

Available Models

AI Tools

On this page