Intelligence Pricing

Pay only for what you use. Provider cost + 5%.

Pricing Formula

Your cost = Provider cost + 5%

The 5% margin covers:

• x402 settlement infrastructure
• Smart routing and reliability
• No API key management
• Instant on-chain payments

What $1 Gets You

Full Price List

OpenAI

Anthropic

Google

xAI

DeepSeek

Meta (via Together/Fireworks)

Qwen

Mistral

Image Generation

Cost Comparison: BlockRun vs Direct

You pay 5% more, but you get:

• No API key management
• No monthly invoices
• No prepaid credits
• One wallet for all providers
• Instant per-request settlement

Budget Management

Session Budgets

from blockrun_llm import LLMClient

# Limit spending per session
client = LLMClient(session_budget=5.00)

Check Balance

balance = client.get_balance()
print(f"${balance} USDC remaining")

Track Spending

# Get usage stats
usage = client.get_usage()
print(f"Spent: ${usage['total_spent']}")
print(f"Requests: {usage['request_count']}")

Cost Optimization Tips

1. Use Cheaper Models for Routine Tasks

# Expensive
response = client.chat("openai/gpt-4o", "Summarize this text")

# 50x cheaper, similar quality
response = client.chat("deepseek/deepseek-v3", "Summarize this text")

2. Use Flash Models for Speed

# For quick, simple tasks
response = client.chat("google/gemini-2.5-flash", prompt)

3. Match Model to Task

4. Optimize Prompts

Shorter prompts = fewer input tokens = lower cost.

No Hidden Fees

• No subscriptions
• No minimums
• No prepaid credits
• No overage charges
• No rate limit fees

Just: provider_cost × 1.05

Payment Details

• Currency: USDC on Base
• Settlement: Instant, on-chain
• Verification: Basescan

Next Steps

• Models Reference
• Intelligence Overview
• Wallet Setup