🤖 AI Model Pricing & Token Arbitrage Radar

🎁 Free Trial Available: Every Apify account receives $5.00 in free monthly usage credits. You can test this Actor and extract up to 1,600+ model pricing records completely FREE without spending a single dollar!

Real-time programmatic intelligence tracking token pricing, context window limits, and cost arbitrage opportunities across 400+ LLMs (OpenAI, DeepSeek, Anthropic Claude, Google Gemini, Meta Llama 3, Mistral, Qwen, and Groq).

---

💡 Why Use This Instead of Expensive SaaS?

Comparison Metric	Manual Model Research / Expensive SaaS	This Apify Actor
Typical Tool	Enterprise AI Observability ($150 ~ $500/mo)	Serverless Pay-Per-Event API
Pricing Model	Heavy Monthly Subscription	Pay only $0.003 per model record
Commitment	Fixed monthly cost	Zero commitment — test free with $5 credit
Cost Efficiency	High fixed overhead	Save 90%+ by dynamically routing to cheaper LLMs
Integration	Manual checking across 10+ provider docs	1-click JSON API / Python / LangChain integration

---

🎯 Key Use Cases

• Dynamic AI Routing: Route simple user queries to ultra-budget models (e.g. DeepSeek / Llama 3.1 8B at $0.05/M) and complex tasks to frontier models (Claude 3.5 Sonnet / GPT-4o), cutting corporate AI bills by 70%~90%.
• AI Agent Builders: Equip your LangChain, LlamaIndex, or AutoGen multi-agent system with real-time model cost discovery tools.
• Cost Benchmark Reports: Generate automated daily/weekly LLM pricing tracking reports for your tech blog or SaaS dashboard.

---

📥 Input Parameters

Field	Type	Description	Default
provider_filter	String	Filter by provider (all, openai, deepseek, anthropic, meta-llama, google)	all
max_prompt_price_per_m	Number	Max input token price in USD per 1M tokens	100.0
min_context_length	Integer	Minimum required context window (tokens)	8192
sort_by	String	Sort order: lowest_prompt_price, highest_context	lowest_prompt_price
max_items	Integer	Max model records to extract	50

---

📤 Sample Output (JSON)

{
  "model_id": "deepseek/deepseek-chat",
  "model_name": "DeepSeek-V3",
  "provider": "deepseek",
  "prompt_price_per_m": 0.14,
  "completion_price_per_m": 0.28,
  "context_length": 64000,
  "tokenizer": "DeepSeek",
  "description": "DeepSeek-V3 is a strong open-weight MoE model offering frontier-grade reasoning at a fraction of GPT-4 cost.",
  "is_free": false,
  "cost_tier": "Ultra-Budget (< $0.50/M)",
  "arbitrage_recommendation": "Top Arbitrage Candidate: 90%+ cheaper than GPT-4 with massive 64k+ context window.",
  "openrouter_url": "https://openrouter.ai/models/deepseek/deepseek-chat",
  "scraped_at": "2026-09-08T04:30:00Z"
}

---

💻 1-Click Code Integration (Python)

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")
run_input = {
    "provider_filter": "all",
    "max_prompt_price_per_m": 1.0,
    "min_context_length": 32000,
    "sort_by": "lowest_prompt_price",
    "max_items": 20
}
run = client.actor("robinworld/ai-model-pricing-token-arbitrage").call(run_input=run_input)

for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(f"[{item['provider']}] {item['model_name']} - ${item['prompt_price_per_m']}/M (Context: {item['context_length']:,})")

---

🔄 Integrations & Export Workflows

• 📊 Spreadsheets: 1-click export to Google Sheets, Excel, or CSV.
• ⚡ No-Code Automation: Trigger workflows in Make.com, Zapier, or n8n.
• 🤖 AI Agents: Direct tool integration for LangChain, CrewAI, and Claude MCP.

---

❓ Frequently Asked Questions (FAQ)

Q: Do I need API keys for individual LLM providers?
A: No! This Actor queries public registry index feeds, so no provider keys or proxies are required.

Q: How fresh is the pricing data?
A: Live real-time pricing directly fetched from verified provider registries on every run.

Q: How do I test this for free?
A: Just click "Start" with default inputs! Your Apify monthly free credits cover your testing completely.

---

⭐ Feedback & Community Support

If you find this Actor valuable, please leave a 5-star review on the Apify Store! For custom provider requests, open an issue in the Issues tab.