Getting Started

LLM Resayil is an OpenAI-compatible API that lets you access 45+ open-source and cloud LLM models with flexible billing. Any OpenAI SDK works seamlessly by overriding the base URL.

Setup in 5 Steps

1. Register at llm.resayil.io/register
2. Subscribe at /billing/plans — choose a plan or start your free 7-day trial
3. Create API Key at /api-keys — click "Create Key" and save it (shown only once)
4. Make your first call:

curl https://llm.resayil.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

5. Track usage at /dashboard

How do I authenticate API requests?

Every API request requires authentication using your API key in the Authorization header.

Header Format

Authorization: Bearer YOUR_API_KEY

Getting Your API Key

Visit /api-keys to create and manage keys. Your key is shown only once at creation — store it securely.

Key Limits by Plan

Security Best Practices

• Never commit API keys to version control — use environment variables
• Rotate keys regularly
• Use separate keys per application or environment
• Revoke keys immediately if compromised
• Omit keys from error messages and logs

How do I send a chat completion request?

The base URL for all API requests is:

POST /api/v1/chat/completions

Send messages to a model and get a completion response. Supports streaming via the stream parameter.

Request Parameters

Example Request

curl https://llm.resayil.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:3b",
    "messages": [
      {"role": "user", "content": "What is 2 + 2?"}
    ],
    "temperature": 0.7,
    "max_tokens": 100
  }'

Example Response

{
  "id": "chatcmpl-abc123def456",
  "object": "chat.completion",
  "created": 1740000000,
  "model": "llama3.2:3b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "2 + 2 equals 4."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

GET /api/v1/models

List all available models. Returns an array of model objects with metadata.

Example Response

{
  "object": "list",
  "data": [
    {
      "id": "llama3.2:3b",
      "object": "model",
      "owned_by": "meta",
      "context_window": 8192,
      "credit_cost_multiplier": 1,
      "is_active": true
    },
    {
      "id": "qwen2.5:7b",
      "object": "model",
      "owned_by": "alibaba",
      "context_window": 131072,
      "credit_cost_multiplier": 1,
      "is_active": true
    },
    {
      "id": "claude-3-sonnet-cloud",
      "object": "model",
      "owned_by": "anthropic",
      "context_window": 200000,
      "credit_cost_multiplier": 2,
      "is_active": true
    }
  ]
}

Which AI models are available?

Access 45+ LLM models spanning local open-source and cloud providers. Fetch available models using:

curl https://llm.resayil.io/api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Model Families

Credit Costs

Each API request consumes credits based on total tokens (prompt + completion) multiplied by the model's credit multiplier. Check your model list response for the credit_cost_multiplier field.

Billing & Credits

LLM Resayil uses a credit-based system. Each subscription plan includes monthly credits, and additional credits can be purchased via top-up packs.

Credit Costs by Model Type

Monthly Plans

Free Trial

New accounts receive a 7-day free trial with 5,000 trial credits. No payment method required.

Credit Top-ups

When your monthly credits run out, purchase additional credits:

Monitoring Usage

Track your credit balance and usage breakdown in your dashboard.

What are the API rate limits?

API requests are rate-limited on a per-key basis using a rolling 1-minute window.

Rate Limits by Plan

Exceeding Limits

When you exceed your rate limit, the API returns a 429 Too Many Requests response:

{
  "error": {
    "code": "429",
    "message": "Rate limit exceeded. Max 10 requests per minute."
  }
}

Recommended Strategy

Implement exponential backoff when receiving 429 responses:

• First retry: wait 1 second
• Second retry: wait 2 seconds
• Third retry: wait 4 seconds
• And so on, doubling each time

Upgrade Your Plan

Need higher limits? upgrade your subscription or contact support for Enterprise tier options.

What errors can the API return?

All error responses follow this format:

{
  "error": {
    "code": "ERROR_CODE",
    "message": "Human-readable error message"
  }
}

Common Errors

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or missing API key"
  }
}

{
  "error": {
    "code": "insufficient_credits",
    "message": "Insufficient credits. Please top up your account."
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Rate limit exceeded. Max 10 requests per minute."
  }
}

{
  "error": {
    "code": "service_unavailable",
    "message": "Model service is temporarily unavailable. Please retry shortly."
  }
}

Code Examples

Below are complete working examples in multiple languages and platforms. Replace YOUR_API_KEY with your actual key.

curl https://llm.resayil.io/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:3b",
    "messages": [
      {"role": "user", "content": "Tell me a joke."}
    ]
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.resayil.io/api/v1"
)

response = client.chat.completions.create(
    model="llama3.2:3b",
    messages=[
        {"role": "user", "content": "Tell me a joke."}
    ]
)

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

// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://llm.resayil.io/api/v1',
});

const completion = await client.chat.completions.create({
  model: 'llama3.2:3b',
  messages: [
    { role: 'user', content: 'Tell me a joke.' },
  ],
});

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

{
  "model": "llama3.2:3b",
  "messages": [
    {
      "role": "user",
      "content": "{{ $json.input }}"
    }
  ]
}