BYO API Key

AI Costs & LLM Pricing

K8 Inspector uses your own Anthropic API key for AI features. Understand exactly what it costs and how to control spending.

Bring Your Own API Key. K8 Inspector connects directly to Anthropic using your API key. No markup, no middleman, no hidden fees. You pay Anthropic at their published rates and have full control over your usage.

Important: What You Need to Know

Before You Start

  • API key required: AI features will not work without a valid Anthropic API key
  • Separate billing: Anthropic bills you directly; K8 Inspector does not process or see your API charges
  • Your responsibility: You are responsible for monitoring your Anthropic usage and costs
  • Rate limits apply: Anthropic rate limits apply to your account; heavy usage may require higher tier
  • Data sent to Anthropic: Cluster metadata (names, statuses, events, logs) is sent for analysis; secrets are never sent
  • Prices may change: Anthropic may adjust pricing; always verify current rates at anthropic.com

Anthropic Claude Pricing (2026)

Model Input Tokens Output Tokens Used For
Claude Sonnet 4 $3.00 / 1M tokens $15.00 / 1M tokens Complex analysis, RCA, debugging
Claude Haiku 3.5 $0.80 / 1M tokens $4.00 / 1M tokens Simple queries, listing, filtering

Source: anthropic.com/pricing - Always verify current rates before relying on these estimates.

Estimated Monthly Costs

Light Usage
$3-8
5-10 queries/day
Solo dev / learning
Moderate
$15-40
20-50 queries/day
Small team
Heavy
$75-150
100-200 queries/day
Active operations
Enterprise
$300+
500+ queries/day
Large teams

Estimates Only

  • Actual costs vary based on query complexity, cluster size, and usage patterns
  • Larger clusters (more pods/nodes) require more tokens to describe
  • Broad queries ("what's wrong?") cost more than specific ones ("show pod X logs")
  • Log-heavy queries can significantly increase token usage

Cost Per Operation

Operation Example Est. Tokens Est. Cost
Simple query "List failing pods in production" ~700 total ~$0.006
Complex query "Why is checkout-service slow?" ~3,000 total ~$0.02
Root cause analysis Automated incident diagnosis ~7,000 total ~$0.05
Full cluster diagnosis "What's wrong with my cluster?" ~10,000 total ~$0.08
YAML generation "Create a deployment for nginx" ~2,300 total ~$0.02
Security explanation CVE context and remediation ~4,500 total ~$0.03

How Costs Are Calculated

Cost = (input_tokens x $0.000003) + (output_tokens x $0.000015)

Example: A complex query with 2,000 input tokens and 1,000 output tokens:
(2,000 x $0.000003) + (1,000 x $0.000015) = $0.006 + $0.015 = $0.021

Controlling Your Costs

K8 Inspector provides built-in controls to help manage your API spending.

Control Default Description
Queries per minute 10 Prevents runaway automated queries
Queries per hour 100 Hourly usage cap
Queries per day 500 Daily maximum queries
Max tokens per query 8,000 Limits context sent to AI
Monthly budget cap Unlimited Disables AI when budget reached
# Example .env configuration

# Rate limits
AI_RATE_LIMIT_PER_MINUTE=10
AI_RATE_LIMIT_PER_DAY=500

# Budget controls
AI_MONTHLY_BUDGET_CAP=50 # USD - AI disabled when reached
AI_BUDGET_WARNING_THRESHOLD=80 # Alert at 80% of budget

# Use cheaper model for simple queries
AI_MODEL_SIMPLE_QUERIES=claude-3-haiku
AI_MODEL_COMPLEX_ANALYSIS=claude-sonnet-4

Tips to Reduce Costs

Be Specific

"Show failing pods in namespace payments" costs less than "Show me everything wrong." Targeted queries require less context.

Use Haiku for Simple Tasks

Configure K8 Inspector to use Claude Haiku for list/filter operations. It's 75% cheaper than Sonnet for basic queries.

Enable Response Caching

Repeated similar queries can use cached context, reducing token usage and API calls.

Set Budget Caps

Configure a monthly budget cap to automatically disable AI features before costs exceed your threshold.

Disable Auto-Analysis

For non-critical dev clusters, disable automatic AI analysis and use manual triggers only.

Monitor in Anthropic Console

Track your actual usage in the Anthropic Console. Set up billing alerts directly with Anthropic.

Frequently Asked Questions

Can I use K8 Inspector without an API key?

Yes. All core Kubernetes management features work without an API key. AI-powered features (assistant, auto-analysis, intelligent insights) will be disabled, but dashboards, logs, resource management, and security scanning work fully.

Where do I get an API key?

Sign up at console.anthropic.com to create an Anthropic account and generate an API key. You'll need to add payment information to your Anthropic account.

Is my cluster data safe?

When you use AI features, cluster metadata (resource names, statuses, events, log snippets) is sent to Anthropic for analysis. Secret contents are never sent. You can further restrict what's shared via configuration. Review Anthropic's data policies for their handling practices.

What if I exceed Anthropic's rate limits?

Anthropic applies rate limits based on your account tier. If you hit their limits, queries will fail temporarily. Consider upgrading your Anthropic account tier for higher limits, or configure K8 Inspector's rate limits to stay within your allocation.

Can I use a different LLM provider?

Currently, K8 Inspector is optimized for Anthropic Claude. Support for additional providers may be added in future releases. Check our documentation for the latest supported providers.

How do I track my spending?

Monitor your usage in K8 Inspector's Settings > AI Usage panel for estimates. For authoritative billing information, check the Anthropic Console directly. We recommend setting up Anthropic billing alerts.

Ready to Get Started?

Download K8 Inspector free. Add your Anthropic API key when you're ready to unlock AI features.

Download K8 Inspector Get Anthropic API Key