LLM Prices

Stop hardcoding prices. Use our API instead.

Real-time LLM API Pricing

Compare actual prices across OpenAI, Claude, Google, and other leading AI models. Get live pricing data to optimize your AI costs.

Browse Models View API Docs

Real-time Data

Updated hourly

Easy Integration

Simple REST API

All Providers

OpenAI, Claude & more

Free to Use

No API key needed

api-example.py

import requests

# Fetch pricing for GPT-4o
response = requests.get('https://llmprices.ai/api/pricing?model=openai/gpt-4o')
data = response.json()

print(data['pricing'])

OpenAI & Claude Models

Live pricing for all OpenAI and Anthropic models

0 models

API Documentation

Integrate real-time pricing data into your applications

Loading models...

GEThttps://llmprices.ai/api/pricing?model=:modelFast Response

Get pricing for any model by passing the model ID as a query parameter. Simple and convenient - just one GET request. Our API is optimized for speed with sub-100ms response times and hourly caching.

Example Request

GET https://llmprices.ai/api/pricing?model=openai/gpt-4o

Response

{
  "id": "openai/gpt-4o",
  "name": "OpenAI: GPT-4o",
  "pricing": {
    "prompt": "0.0000025",
    "completion": "0.00001",
    "input_cache_read": "0.00000125"
  }
}

Response Fields

• id - Model identifier
• name - Human-readable model name
• pricing.prompt - Input token price (per token)
• pricing.completion - Output token price (per token)
• pricing.input_cache_read - Cached input token price (when available)
Note: All prices are per token. Multiply by 1,000,000 to get price per 1M tokens

Performance

• Response time: <100ms average
• Cache duration: 1 hour (3600 seconds)
• Rate limit: No limits for public use
• Uptime: 99.9% availability