Add LLM access to your SaaS in 15 minutes

This guide walks you through adding LLM access to your SaaS platform using Unlimited subscriptions — dedicated model access with guaranteed throughput and no token counting. By the end, your users will each have their own API key with unlimited usage during subscribed hours.

What you’ll build

• A management key to control your platform’s subscriptions
• Unlimited subscriptions for your users (Asia, Europe, or Americas time blocks)
• API keys assigned to each user
• Your users calling our API with their own keys

Prerequisites

• A CheapestInference account (create one)
• A saved payment method (add a card from the dashboard or via your first checkout)

Step 1: Get your management key (2 min)

Log into your dashboard and navigate to Keys. Create a Management Key — this authenticates all platform operations.

mk_your_management_key_here

Keep this key secure. It can create subscriptions, keys, and manage billing.

Step 2: List available Unlimited plans (2 min)

Each Unlimited plan is a dedicated model with guaranteed capacity during specific time blocks:

curl https://api.cheapestinference.com/api/pools \
  -H "Authorization: Bearer mk_your_management_key"

Response:

{
  "success": true,
  "data": [
    {
      "id": "pool_uuid",
      "slug": "kimi26",
      "modelName": "Kimi 2.6, GLM 5.1, MiniMax 2.5",
      "minPricePerDay": "39.00",
      "annualDiscount": 0.15,
      "totalSlots": 100,
      "pledgedSlots": 3
    }
  ]
}

Step 3: Subscribe to a time block (3 min)

Choose which 8-hour UTC block your user needs:

Block	Hours (UTC)	Best for
asia	00:00–07:59	Asia-Pacific users
europe	08:00–15:59	Europe / Middle East
americas	16:00–23:59	Americas users

Subscribe your user to a block:

curl -X POST https://api.cheapestinference.com/api/pools/kimi26/subscribe \
  -H "Authorization: Bearer mk_your_management_key" \
  -H "Content-Type: application/json" \
  -d '{
    "blocks": ["americas"],
    "quantity": 1,
    "billingCycle": "month"
  }'

Response:

{
  "success": true,
  "data": {
    "id": "subscription_uuid",
    "poolId": "pool_uuid",
    "status": "active",
    "monthlyPrice": "39.00",
    "hours": [
      { "hour": 16, "slotIndex": 1, "pricePerDay": "4.87" },
      { "hour": 17, "slotIndex": 1, "pricePerDay": "4.87" }
    ],
    "key": null
  }
}

No API key is created automatically — you’ll create it in the next step.

Step 4: Create the API key (2 min)

Create an API key for your user’s subscription:

curl -X POST https://api.cheapestinference.com/api/keys/subscription \
  -H "Authorization: Bearer mk_your_management_key" \
  -H "Content-Type: application/json" \
  -d '{"subscriptionId": "subscription_uuid"}'

Response:

{
  "success": true,
  "data": {
    "id": "key_uuid",
    "apiKey": "sk_pool_abc123xxxxxxxx",
    "isActive": true
  }
}

Unlimited throughput — no RPM or TPM caps. The only limit is 1 concurrent request per key. Your user’s key works 24/7 during their subscribed block.

Step 5: Your user makes a request (5 min)

Your user hits our API with their key. It’s a standard OpenAI-compatible endpoint:

Python:

from openai import OpenAI

client = OpenAI(
    api_key="sk_pool_abc123xxxxxxxx",
    base_url="https://api.cheapestinference.com/v1"
)

response = client.chat.completions.create(
    model="moonshot/kimi-k2.6",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

Node.js:

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk_pool_abc123xxxxxxxx',
  baseURL: 'https://api.cheapestinference.com/v1',
});

const response = await client.chat.completions.create({
  model: 'moonshot/kimi-k2.6',
  messages: [{ role: 'user', content: 'Hello!' }],
});

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

Step 6: Manage multiple users (5 min)

List all your subscriptions and their keys:

# List all subscriptions for a pool
curl https://api.cheapestinference.com/api/pools/kimi26/my-subscriptions \
  -H "Authorization: Bearer mk_your_management_key"

# List all your keys on this pool
curl https://api.cheapestinference.com/api/pools/kimi26/my-keys \
  -H "Authorization: Bearer mk_your_management_key"

To add a user to another time block:

# Subscribe to europe block for a new user
SUB=$(curl -s -X POST https://api.cheapestinference.com/api/pools/kimi26/subscribe \
  -H "Authorization: Bearer mk_your_management_key" \
  -H "Content-Type: application/json" \
  -d '{"blocks": ["europe"], "quantity": 1, "billingCycle": "month"}')

SUB_ID=$(echo $SUB | python3 -c "import sys,json; print(json.load(sys.stdin)['data']['id'])")

curl -X POST https://api.cheapestinference.com/api/keys/subscription \
  -H "Authorization: Bearer mk_your_management_key" \
  -H "Content-Type: application/json" \
  -d "{\"subscriptionId\": \"$SUB_ID\"}"

What’s next

• Unlimited Subscriptions API — full endpoint reference
• Management API — all platform operations
• Models — see all available models

---

Questions? Contact [email protected].