Key Features

Base URL

All API requests should be made to:

https://frostai.xyz/v1

Quick Start

Get up and running with Frost AI in under 5 minutes.

from openai import OpenAI
    
    # Initialize the client with Frost AI
    client = OpenAI(
        base_url="https://frostai.xyz/v1",
        api_key="your-api-key"
    )

# Make a chat completion request
response = client.chat.completions.create(
    model="claude-opus-4-5",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

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

import OpenAI from 'openai';

// Initialize the client with Frost AI
const client = new OpenAI({
    baseURL: 'https://frostai.xyz/v1',
    apiKey: 'your-api-key'
});

// Make a chat completion request
const response = await client.chat.completions.create({
    model: 'claude-opus-4-5',
    messages: [
        { role: 'user', content: 'Hello, how are you?' }
    ]
});

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

curl https://frostai.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "claude-opus-4-5",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ]
  }'

Authentication

All API requests require authentication using your API key.

API Keys

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Environment Variables

We recommend storing your API key in an environment variable:

export FROST_API_KEY="your-api-key"

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://frostai.xyz/v1",
    api_key=os.environ.get("FROST_API_KEY")
)

Credits & Billing

Understand how Frost AI credits work and how you're billed.

How Credits Work

Credit Usage

Credits are deducted based on token usage at official provider rates:

• Input tokens: Charged per 1M tokens at the model's input rate
• Output tokens: Charged per 1M tokens at the model's output rate
• Credits never expire: Use them at your own pace

Model Pricing

Here are the pricing rates for popular models (per 1M tokens):

Check Your Balance

You can check your credit balance via the API:

curl https://frostai.xyz/v1/account/credits \
  -H "Authorization: Bearer your-api-key"

Tier System

Frost AI offers different tiers with varying benefits and rate limits.

Available Tiers

Context Window Examples

Tier Benefits

Upgrade Your Tier

You can upgrade your tier in several ways:

• Purchase Credits: Buying larger credit packages may include tier upgrades
• Promo Codes: Use special promo codes for tier upgrades
• Contact Sales: For Enterprise tier, contact our sales team

Promo Codes

Use promo codes to get free credits, tier upgrades, and special discounts.

Types of Promo Codes

How to Use Promo Codes

Account Approval

Learn about the account approval process and whitelist system.

Approval Process

What Happens While Pending?

• You can log in but will see a "Pending Approval" screen
• You cannot access the Dashboard or make API calls
• Your API keys are created but won't work until approved
• You'll receive an email notification once approved

Need Faster Approval?

Contact our support team with your use case for expedited review:

• Email: support@frostai.xyz
• Discord: Join our community server
• Support Ticket: Create a ticket in the Dashboard (after approval)

Chat Completions

Create chat completions with any supported model.

Endpoint

Request Body

Example Request

response = client.chat.completions.create(
    model="claude-opus-4-5",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ],
    temperature=0.7,
    max_tokens=1000
)

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1702488000,
  "model": "claude-opus-4-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Streaming

Receive responses as they're generated for better user experience.

Enable Streaming

Set stream: true in your request to receive Server-Sent Events (SSE):

stream = client.chat.completions.create(
    model="claude-opus-4-5",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

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

const stream = await client.chat.completions.create({
    model: 'claude-opus-4-5',
    messages: [{ role: 'user', content: 'Tell me a story' }],
    stream: true
});

for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Error Handling

Learn how to handle API errors gracefully.

Error Response Format

{
  "error": {
    "message": "Invalid API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Common Error Codes

Context Limit Error

When your request exceeds your tier's context window limit, you'll receive a 413 error:

{
  "error": {
    "message": "Context window limit exceeded. Your tier allows 32,768 tokens, but your request contains 45,000 tokens.",
    "type": "context_limit_exceeded",
    "code": "context_limit_exceeded",
    "tier": "free",
    "limit": 32768,
    "used": 45000,
    "exceeded": 12232
  }
}

Handling Errors in Python

from openai import OpenAI, APIError, RateLimitError

try:
    response = client.chat.completions.create(
        model="claude-opus-4-5",
        messages=[{"role": "user", "content": "Hello"}]
    )
except RateLimitError:
    print("Rate limited. Please wait and retry.")
except APIError as e:
    print(f"API error: {e}")

Rate Limits

Understanding and working with API rate limits and context window limits.

Rate Limits by Tier

Rate Limit Headers

Check these headers in API responses:

• X-RateLimit-Limit-Minute: Max requests per minute
• X-RateLimit-Limit-Hour: Max requests per hour
• X-RateLimit-Limit-Day: Max requests per day
• X-RateLimit-Tier: Your current tier
• Retry-After: Seconds until you can retry (when rate limited)

Context Limit Headers

When context limit is exceeded (HTTP 413), these headers are included:

• X-Context-Limit: Your tier's context window limit
• X-Context-Used: Tokens in your request
• X-Context-Tier: Your current tier

Models API

List and get information about available models.

List Models

models = client.models.list()

for model in models:
    print(model.id)