Quick Start

Get your first LLM request through ModelHive in under 2 minutes.

Prerequisites

• A ModelHive account (sign up here)
• An API key (created from the dashboard)

Step 1: Get Your API Key

After signing up and completing onboarding:

1. Go to Dashboard → API Keys
2. Click Create New Key
3. Set a name, budget, and optionally restrict to specific models
4. Copy your API key (starts with sk-)

warning

Store your API key securely. It will only be shown once at creation time.

Step 2: Make Your First Request

ModelHive is fully OpenAI-compatible. Use any OpenAI SDK or HTTP client.

Python (OpenAI SDK)

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is semantic caching?"}
    ]
)

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

JavaScript (OpenAI SDK)

import OpenAI from 'openai';

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

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is semantic caching?' },
  ],
});

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

cURL

curl -X POST https://api.modelhive.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-modelhive-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is semantic caching?"}
    ]
  }'

Step 3: Verify It Worked

Check your response. You'll notice ModelHive enriches the response with metadata:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [...],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  },
  "_modelhive": {
    "cache_status": "MISS",
    "cost_estimate": 0.0032,
    "guardrails_passed": true
  }
}

Step 4: Try a Cached Request

Make the same request again — this time HiveCache will detect the semantic similarity:

# Same request → HiveCache DIRECT hit
curl -X POST https://api.modelhive.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-modelhive-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is semantic caching?"}
    ]
  }'

The response will include "cache_status": "DIRECT" — served instantly from cache at a fraction of the cost.

What's Next?

• Authentication — Learn about JWT tokens and API key authentication
• HiveCache — Deep dive into the semantic cache engine
• HiveState — Adaptive state compression for long conversations
• HiveRoute — Intelligent model routing based on task complexity
• Guardrails — Configure security protections for your LLM calls
• API Reference — Browse the complete API endpoint documentation