OpenClaw API Monitor v2.0

API monitoring, cost tracking, and intelligent routing for AI providers. 5 tools. Real-time status. Budget alerts.

What's New in v2.0

• APIWatch Engine -- Real-time status monitoring for 20+ AI providers using official status pages + synthetic probes every 2 minutes.
• CostLens -- Unified cost tracking across OpenAI, Anthropic, Groq, DeepInfra, and 16 more providers. See your true total AI spend in one number.
• SmartRoute -- Recommends the optimal provider for each task type based on current uptime, latency, rate limit headroom, and cost-per-token.
• BudgetGuard -- Hard and soft limits. Soft limit sends Telegram alert. Hard limit automatically routes calls away from the over-budget provider.

Quick Start

{
  "openclaw-api-monitor": {
    "type": "streamable-http",
    "url": "https://openclaw-api-monitor-mcp.yagami8095.workers.dev/mcp"
  }
}

Add to Claude Desktop, Cursor, Windsurf, VS Code, or any MCP-compatible client. Zero install. Works immediately.

Detection Triggers

This skill activates when a user says any of these:

• "is OpenAI down", "Anthropic API status", "check Groq", "provider status", "API outage"
• "how many tokens used", "API usage stats", "calls today", "usage this month", "token count"
• "alert at $50", "budget limit", "notify when spend hits", "API budget", "spending alert"
• "cost breakdown", "spending per provider", "GPT-4 cost", "API cost analysis", "cost per model"
• "cheapest model for this", "fastest API", "route to best provider", "optimize API selection"
• "rate limit", "rate limit remaining", "quota", "how many calls left today"

Named Protocols

APIWatch Engine

Continuous status monitoring across the AI provider ecosystem:

Monitored providers (20+):

Status determination:

Probe method: Synthetic API call (cheapest model, 1-token completion) every 2 minutes from Cloudflare edge.

SmartRoute Protocol

Recommendation engine for provider selection:

Scoring factors:

Task types and their routing preferences:

BudgetGuard Levels

Tools (5)

check_api_status -- Real-Time Provider Status via APIWatch Engine

Check current status of any AI provider or get a full ecosystem status dashboard.

Wrong / Right:

WRONG: Sending a failing API call to OpenAI 10 times before checking if they're down
RIGHT: check_api_status({ provider: "openai" })
       -> { status: "partial_outage", affected: ["gpt-4o", "o1"],
            operational: ["gpt-4o-mini", "text-embedding-3"],
            incident: "Elevated error rates on flagship models since 14:32 UTC",
            eta_resolved: "~30 minutes (per status page)" }
       -> Know before you retry. Save tokens and sanity.

WRONG: check_api_status({ provider: "openai" }) as a replacement for proper retry logic
RIGHT: APIWatch tells you the current state. Your application should still implement
       exponential backoff and retry for transient errors.

get_usage_stats -- Usage Analytics via CostLens

Get token usage, call counts, and costs aggregated across all connected providers.

Wrong / Right:

WRONG: Checking 5 separate provider dashboards to understand total AI spend
RIGHT: get_usage_stats({ range: "this_month" })
       -> { total_cost_usd: 12.47, total_tokens: 8_420_000, total_calls: 3_214,
            by_provider: [
              { provider: "deepinfra", cost: 7.23, tokens: 6_100_000 },
              { provider: "groq", cost: 0.00, tokens: 1_800_000 },
              { provider: "anthropic", cost: 5.24, tokens: 520_000 }
            ] }
       -> One call. True total. Actionable breakdown.

WRONG: Expecting usage_stats to track calls made outside this toolkit
RIGHT: get_usage_stats only tracks calls made through your connected provider API keys.
       Calls made directly via provider dashboards or other tools are not counted.

set_budget_alert (Pro) -- Budget Notification via BudgetGuard

Set a spending threshold that triggers Telegram alerts and optional auto-routing.

Parameters: provider (or "all"), budget_usd, period (daily/monthly), telegram_chat_id, hard_limit (bool)

get_cost_breakdown -- Detailed Cost Analysis via CostLens

Get a detailed cost breakdown by provider, model, and time period with efficiency metrics.

Returns: cost per model, cost per 1M tokens, trend (up/down/stable vs prior period), most expensive calls, cost optimization suggestions

optimize_routing -- Provider Recommendation via SmartRoute Protocol

Get a recommendation for which provider and model to use for a given task.

Parameters: task_type (reasoning/fast-chat/code/json/search/image), budget_constraint (optional $/1M tokens max), latency_requirement (optional ms max)

Returns: primary recommendation (provider, model, reason), fallback option, current_cost_per_1m_tokens, current_latency_p50_ms, status

Security & Privacy

• API keys encrypted -- Provider API keys stored with AES-256 encryption. Never returned in API responses, never logged.
• Usage data stays yours -- Your usage statistics are scoped to your Pro key and never aggregated with other users' data.
• Read-only key scopes -- For usage stats, we only require read-only API access where providers support it (OpenAI usage scope, etc.).
• No call interception -- API Monitor tracks via provider APIs, not by proxying your calls. Your API calls go directly to providers, not through our servers.
• Budget hard limits are local -- Hard limit enforcement happens at the APIWatch Edge level and does not require any changes to your application code.
• HTTPS only -- All connections are TLS 1.3. HTTP is rejected.

Pricing

Get Pro Key: https://buy.stripe.com/4gw5na5U19SP9TW288

The OpenClaw Intelligence Stack

All 9 servers share one Pro key. $9/mo = 49 tools.