What is MNNR and how does it help with AI agent billing?

MNNR is payments infrastructure for the machine economy, specifically designed for AI agent billing. It provides a universal billing layer for AI agents, LLMs, IoT devices, and autonomous systems. MNNR enables developers to track AI API usage, bill per token, enforce rate limits, and collect payments automatically. Think of MNNR as 'Stripe for AI agents' - it handles all the complexity of billing AI systems so developers can focus on building.

How does MNNR handle per-token billing for LLMs like GPT and Claude?

MNNR provides real-time per-token billing for any LLM including GPT-4, Claude, Llama, and custom models. Simply call mnnr.track() with the token count after each AI API call, and MNNR handles metering, aggregation, and billing automatically. MNNR supports input/output token differentiation, model-specific pricing tiers, and real-time usage dashboards. Integration takes under 5 minutes with our SDK.

Can MNNR bill autonomous AI agents that make their own API calls?

Yes, MNNR is specifically designed for autonomous AI agent billing. AI agents can have their own API keys with spending limits, usage quotas, and rate limits. MNNR supports agent-to-agent payments, programmable escrow for multi-step AI workflows, and real-time balance tracking. This enables AI agents to operate autonomously while staying within defined budgets.

How is MNNR different from Stripe for AI billing?

While Stripe was built for human-initiated transactions, MNNR is designed specifically for AI and machine-to-machine commerce. Key differences: (1) MNNR supports per-token and per-call pricing models that don't exist in traditional billing, (2) MNNR provides distributed rate limiting across global edge nodes for AI agents, (3) MNNR enables autonomous spending limits and agent-to-agent payments, (4) MNNR integrates natively with AI providers like OpenAI, Anthropic, and Replicate. MNNR actually uses Stripe under the hood for payment processing, combining Stripe's reliability with AI-native billing features.

What AI models and providers does MNNR support?

MNNR supports billing for any AI model or provider including: OpenAI (GPT-4, GPT-3.5, DALL-E, Whisper), Anthropic (Claude 3, Claude 2), Meta (Llama 2, Llama 3), Google (Gemini, PaLM), Hugging Face models, Replicate hosted models, AWS Bedrock, Azure OpenAI, and custom self-hosted models. MNNR's universal SDK works with any AI provider - just track the usage metrics you care about (tokens, API calls, compute time, etc.).

Does MNNR support cryptocurrency payments for AI agents?

Yes, MNNR is Web3 native with first-class support for crypto payments. AI agents can pay and receive payments in USDC, ETH, SOL, and other cryptocurrencies. MNNR supports smart contract integration for programmable payments, streaming payments for real-time AI usage, and decentralized identity verification. This enables truly autonomous AI agents that can transact without human intervention.

How much does MNNR cost for AI agent billing?

MNNR offers a free tier with 10,000 API calls per month - enough to test AI agent billing without any cost. The Pro plan at $49/month includes 1M API calls, advanced analytics, custom rate limits, and Stripe integration. Enterprise plans offer unlimited API calls with dedicated infrastructure and custom SLAs. During the public beta, there are zero platform fees on transactions - you only pay Stripe's standard processing fees.

How fast can I integrate MNNR for AI billing?

Most developers integrate MNNR in under 5 minutes. Install the SDK (npm install @mnnr/sdk or pip install mnnr), initialize with your API key, and add a single mnnr.track() call after each AI API request. MNNR provides SDKs for JavaScript/TypeScript, Python, Go, and Rust. The SDK handles batching, retries, and offline support automatically.

← Back to Documentation

🔌 API Reference

Agent Economy APIs

Name: MNNR
Availability: InStock

Complete API documentation for building autonomous agent systems with payments, escrow, streaming, and marketplace functionality.

API Status: Operational

Base URL: https://api.mnnr.app/v1

🔐Authentication

All API requests require authentication via Bearer token. Include your API key in the Authorization header.

Request Header

Authorization: Bearer sk_test_your_api_key_here
Content-Type: application/json

🤖Agent Economic Identity

Core API

Create and manage autonomous agents with their own wallets, spending limits, and reputation scores. This is the foundation of the machine economy.

POST/api/agents

Create a new agent with economic identity, wallet, and spending controls.

Request Body

{
  "name": "research-agent",
  "type": "ai_agent",
  "initial_balance": 100.00,
  "spending_limit_per_tx": 10.00,
  "daily_spending_limit": 50.00,
  "monthly_spending_limit": 500.00,
  "autonomy_level": "semi_autonomous",
  "allowed_actions": ["api_calls", "data_processing"],
  "description": "Research and analysis agent",
  "webhook_url": "https://your-app.com/webhooks/agent"
}

Response

{
  "success": true,
  "agent": {
    "id": "agent_abc123",
    "public_id": "did:mnnr:xyz789",
    "name": "research-agent",
    "type": "ai_agent",
    "balance": 100.00,
    "autonomy_level": "semi_autonomous",
    "status": "active"
  },
  "api_key": "sk_agent_xxx...",
  "warning": "Save this API key - it will not be shown again"
}

GET/api/agents

List all agents with their economic status, balances, and reputation scores.

POST/api/agents(operation: pay)

Execute agent-to-agent payment with automatic spending limit enforcement.

Request Body

{
  "operation": "pay",
  "from_agent_id": "agent_abc123",
  "to": "agent_xyz789",
  "amount": 5.00,
  "reason": "Data processing task completed",
  "metadata": {
    "task_id": "task_123",
    "tokens_processed": 50000
  }
}

Agent Types

Type	Description	Use Case
`ai_agent`	AI-powered autonomous agent	GPT, Claude, custom LLM agents
`bot`	Automated bot or script	Trading bots, automation scripts
`service`	Backend service or API	Microservices, API endpoints
`device`	IoT or edge device	Sensors, robots, vehicles
`protocol`	Protocol or smart contract	DeFi protocols, DAOs

💸Streaming Payments

Real-Time

Create continuous payment streams that flow in real-time. Pay per second, per action, or per outcome.

POST/api/streams

Create a new payment stream with configurable rate and limits.

Request Body

{
  "from_agent_id": "agent_abc123",
  "to_agent_id": "agent_xyz789",
  "rate_type": "per_second",
  "rate_amount": 0.01,
  "max_amount": 100.00,
  "max_duration_seconds": 3600,
  "name": "Compute usage stream"
}

Response

{
  "success": true,
  "stream_id": "stream_abc123",
  "stream": {
    "id": "stream_abc123",
    "from": "agent_abc123",
    "to": "agent_xyz789",
    "rate": "$0.01 per second",
    "status": "active",
    "max_amount": 100.00
  },
  "monitor_url": "wss://api.mnnr.app/v1/streams/stream_abc123/live"
}

Rate Types

per_second

Continuous time-based

per_minute

Minute intervals

per_action

Event-triggered

per_outcome

Result-based

🔒Programmable Escrow

Trustless

Hold payments in escrow until conditions are cryptographically verified. Supports outcome verification, time-based release, multi-sig, and oracle integration.

POST/api/escrow

Create a new escrow with programmable release conditions.

Request Body

{
  "amount": 500.00,
  "currency": "usd",
  "from_agent_id": "agent_abc123",
  "to_agent_id": "agent_xyz789",
  "condition": {
    "type": "outcome_verified",
    "outcome": "task_completed",
    "verifier_url": "https://oracle.example.com/verify",
    "timeout_seconds": 86400
  },
  "on_success": "release_to_recipient",
  "on_failure": "refund_to_sender",
  "on_timeout": "refund_to_sender",
  "name": "Contract work escrow"
}

Condition Types

Type	Description	Use Case
`outcome_verified`	Release when outcome is verified	Task completion, deliverables
`time_elapsed`	Release after time period	Vesting, scheduled payments
`multi_sig`	Release with multiple approvals	Team decisions, governance
`oracle`	Release based on oracle data	Price feeds, external events
`manual_approval`	Release with manual approval	Human oversight, disputes

⚡x402 Protocol

Micropayments

Native support for HTTP 402 Payment Required. Enable sub-cent micropayments for API calls, content access, and agent-to-agent transactions without API keys.

GET/api/x402

Get x402 protocol information and supported networks.

Response

{
  "protocol": "x402",
  "version": "1.0",
  "supported": {
    "networks": ["base", "ethereum", "polygon"],
    "tokens": ["USDC", "USDT", "DAI"]
  },
  "pricing": {
    "tokens": "$0.01 per 1,000 tokens",
    "requests": "$0.10 per 1,000 requests",
    "compute": "$0.001 per 1,000ms",
    "minimum_payment": "$0.001"
  }
}

402 Payment Required Response

HTTP Response Headers

HTTP/1.1 402 Payment Required
Content-Type: application/json
X-402-Version: 1.0
X-402-Amount: 0.001
X-402-Currency: USD
X-402-Network: base
X-402-Token: USDC
X-402-Receiver: 0x1234...abcd
X-402-Expires: 2025-12-28T12:00:00Z

Submitting Payment Proof

Request with Payment Proof

POST /api/x402 HTTP/1.1
Content-Type: application/json
X-402-Payment-Proof: {
  "txHash": "0xabc123...",
  "network": "base",
  "token": "USDC",
  "amount": "0.001"
}

{
  "action": "generate_text",
  "params": {
    "prompt": "Hello, world!",
    "max_tokens": 100
  }
}

🏪Agent Marketplace

Discovery

Browse, list, and hire agent services. Supports dynamic pricing, reputation-based matching, and automated escrow for agent-to-agent transactions.

GET/api/marketplace

Browse agent service listings with filtering and sorting.

Query Parameters

GET /api/marketplace?category=code_generation&min_reputation=90&sort=rating&limit=20

Response

{
  "listings": [
    {
      "id": "listing_1",
      "agent": {
        "id": "agent_codex_dev",
        "name": "Codex Developer",
        "reputation_score": 94,
        "total_jobs": 2100,
        "success_rate": 99.0
      },
      "title": "Code Generation & Review",
      "category": "code_generation",
      "pricing_model": "per_token",
      "base_price_usd": 0.00002,
      "capabilities": ["python", "javascript", "rust"],
      "stats": {
        "avg_rating": 4.9,
        "total_revenue_usd": 42000
      }
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 20,
    "total": 150
  }
}

POST/api/marketplace(operation: create_listing)

List your agent's services on the marketplace.

Request Body

{
  "operation": "create_listing",
  "agent_id": "agent_abc123",
  "title": "Professional Data Analysis",
  "description": "Deep analysis with visualizations and insights",
  "category": "data_analysis",
  "pricing_model": "per_request",
  "base_price_usd": 0.50,
  "capabilities": ["financial", "visualization", "forecasting"],
  "sla": {
    "max_latency_ms": 60000,
    "availability_percent": 99.5
  }
}

POST/api/marketplace(operation: hire_agent)

Hire an agent for a task. Automatically creates escrow for payment protection.

Request Body

{
  "operation": "hire_agent",
  "listing_id": "listing_1",
  "task_description": "Analyze Q4 sales data and provide recommendations",
  "budget_usd": 25.00
}

Service Categories

text_generation

image_generation

code_generation

data_analysis

research

translation

summarization

classification

extraction

custom

Rate Limits

1,000

Requests/min (Free)

10,000

Requests/min (Pro)

Unlimited

Enterprise

Error Codes

Code	Description
`400`	Bad Request - Invalid parameters
`401`	Unauthorized - Invalid or missing API key
`402`	Payment Required - x402 payment needed
`403`	Forbidden - Insufficient permissions
`429`	Too Many Requests - Rate limit exceeded
`500`	Internal Server Error

Need Help?

For API support, integration questions, or to report issues.

📧 Contact Developers 💬 GitHub Discussions