🎯 LLM Radar - AI Model Pricing & Status Hub

The most comprehensive LLM intelligence API - Get real-time pricing for 115 AI models and live operational status from 11 providers in a single API call.

✨ Why LLM Radar?

Building AI applications? You need to know:

• 💰 How much does each model cost? (input/output tokens, cached, batch pricing)
• 🚨 Is the API up right now? (real-time operational status)
• 🏆 How good is the model? (Live LMSYS Arena ELO, Rank, & Vote counts)
• 📊 Which model is best for my task? (capability scores from Costbase)

LLM Radar gives you all of this in one structured JSON response.

🚀 Features

• Live LMSYS Benchmarks: Automatically fetches the latest ELO ratings, ranks, and vote counts from LMSYS Chatbot Arena.
• 115+ Models: Covers OpenAI, Anthropic, Google, Amazon Bedrock, Mistral, and more.
• Unified Pricing: Normalized pricing data (per 1M tokens) across all providers.
• Provider Status: Real-time status checks for 8 major API providers.

---

🏢 Supported Providers & Models

Provider	Models	Highlights
OpenAI	30	GPT-5.1, GPT-5, GPT-4.1, o1, o3-mini, DALL-E, Whisper
Mistral	17	Large, Medium, Small, Codestral, Pixtral, Ministral
Google	11	Gemini 2.5, 2.0, 1.5 Flash/Pro, Imagen, Veo
Groq	11	Llama 3.3/3.2/3.1, Mixtral, Gemma (ultra-fast)
Cohere	10	Command R+, R, Embeddings, Rerank
Amazon	8	Titan, Nova Pro/Lite/Micro, Bedrock Embeddings
xAI	8	Grok 3, Grok 2, Grok Vision
Anthropic	7	Claude Opus/Sonnet/Haiku 4.5, 4, 3.5
Together	6	Llama 3.1 405B/70B, Qwen 2.5, DeepSeek R1
Fireworks	5	Llama 3.3, Qwen 2.5, DeepSeek V3 (serverless)
DeepSeek	2	DeepSeek V3, Reasoner R1

Total: 115 models with detailed pricing & capability scores

---

📊 What You Get

1. Comprehensive Pricing Data

{
  "models": [
    {
      "model_id": "gpt-4.1",
      "provider": "openai",
      "display_name": "GPT-4.1",
      "model_type": "text",
      "tier": "flagship",
      "pricing": {
        "text": {
          "input_per_million": 30.00,
          "output_per_million": 60.00,
          "cached_input_per_million": 15.00
        },
        "context_window": 128000,
        "currency": "USD"
      },
      "benchmarks": {
        "arena_elo": 1287,
        "rank": 24,
        "votes": 24834,
        "coding": 0.94,
        "math": 0.92,
        "source": "LMSYS Chatbot Arena"
      }
    }
  ]
}

2. Real-Time Provider Status

{
  "status": [
    {
      "provider": "openai",
      "status": "operational",
      "description": "All Systems Operational",
      "latency_p50_ms": 145
    },
    {
      "provider": "anthropic",
      "status": "degraded",
      "description": "Increased API Latency"
    }
  ]
}

3. Summary Statistics

{
  "summary": {
    "total_models": 115,
    "providers": {
      "openai": 30,
      "mistral": 17,
      "google": 11,
      "groq": 11,
      "cohere": 10,
      "xai": 8,
      "anthropic": 7,
      "amazon": 8,
      "together": 6,
      "fireworks": 5
    },
    "status_summary": {
      "operational": ["openai", "google", "groq"],
      "degraded": ["anthropic"],
      "outage": []
    }
  }
}

---

💰 Data Fields Included

Category	Fields	Description
Pricing	input_per_million, output_per_million, cached_input_per_million	Token costs in USD
Capability Scores	coding, creative, analysis, translation, math, speed	0-1 scale performance ratings
Model Info	tier, release_date, context_window, max_output_tokens	Model specifications
Status	operational, degraded, outage, unknown	Real-time API health

---

🎯 Model Tiers

Tier	Description	Example Models
flagship	Best performance, highest cost	GPT-5.1, Claude Opus 4.5, Grok 3
standard	Balanced performance/cost	GPT-5-mini, Claude Sonnet, Gemini 2.0
budget	Cost-optimized	GPT-5-nano, Claude Haiku, Ministral 3B
premium	Specialized (reasoning, etc.)	o1, o3-mini, DeepSeek Reasoner

---

🔧 Input Parameters

Parameter	Type	Default	Description
providers	array	["all"]	Which providers to include
dataTypes	array	["pricing", "status"]	What data to fetch
forceRefresh	boolean	false	Bypass cache for fresh pricing

Example Input

{
  "providers": ["openai", "anthropic", "groq"],
  "dataTypes": ["pricing", "status"],
  "forceRefresh": false
}

---

🚀 Use Cases

1. Cost Calculator

const { models } = await llmRadar.getData();
const gpt5 = models.find(m => m.model_id === 'gpt-5.1');
const cost = (tokens / 1_000_000) * gpt5.pricing.text.input_per_million;

2. Find Best Model for Task

const { models } = await llmRadar.getData();
const bestForCoding = models
  .filter(m => m.benchmarks?.coding)
  .sort((a, b) => b.benchmarks.coding - a.benchmarks.coding)[0];
console.log(`Best for coding: ${bestForCoding.display_name}`);

3. Smart Model Router

const { models, status } = await llmRadar.getData();
const operational = status.filter(s => s.status === 'operational').map(s => s.provider);
const cheapest = models
  .filter(m => operational.includes(m.provider) && m.tier === 'budget')
  .sort((a, b) => a.pricing.text.input_per_million - b.pricing.text.input_per_million)[0];

4. Status Dashboard

const { status, summary } = await llmRadar.getData();
console.log(`Operational: ${summary.operational_count}/${status.length}`);
status.forEach(s => showBadge(s.provider, s.status));

---

⚡ Performance

• Fast execution: ~5 seconds per run
• Pricing cached: 30 days (prices rarely change)
• Status fresh: Always real-time from provider APIs
• Minimal compute: Low resource usage per run

---

📡 API Access

After running, access your data via the Apify Dataset API:

curl "https://api.apify.com/v2/datasets/{DATASET_ID}/items" \
  -H "Authorization: Bearer YOUR_TOKEN"

Or use the Apify SDK:

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_TOKEN' });
const run = await client.actor('llm-radar').call();
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].summary); // { total_models: 96, ... }

---

🔄 Data Freshness

Data Type	Cache Duration	Notes
Pricing & Models	30 days	From curated database
Status	Always fresh	Fetched from provider APIs each run

Use forceRefresh: true to bypass pricing cache.

---

⚡ Optimized Usage

1. 🚨 Status Monitor (Save Costs)

Use Case: Check if APIs are down every 15 minutes. Config:

{
  "dataTypes": ["status"],
  "providers": ["all"]
}

Output: Only returns status array. Minimal data transfer.

2. 💰 Pricing & Benchmarks (Full Data)

Use Case: Update your internal database with latest prices and ELO scores. Config:

{
  "dataTypes": ["pricing"],
  "forceRefresh": true
}

📈 Historical Data

The actor automatically snapshots data daily:

• Storage: Key-Value Store
• Key Format: HISTORY_YYYY_MM_DD
• Content: Full pricing & status snapshot

🏷️ Tags

llm ai-pricing openai anthropic claude gpt-5 gemini groq mistral cohere deepseek grok benchmarks lmsys elo status-monitor cost-calculator model-comparison

---

📄 License

ISC

👤 Author

Built by Raihan K.