Telemetry

RelayPlane collects anonymous usage data to improve routing decisions. Here's exactly what we collect and how to opt out.

Telemetry is opt-in (disabled by default). When enabled, we collect anonymous metadata: task type, model, token counts, latency, cost. Your prompts and responses are never collected — they go directly to LLM providers.

What We Collect

Every request generates this exact payload:

1{
2  "device_id": "anon_8f3a2b1c...",
3  "task_type": "code_review",
4  "model": "claude-sonnet-4",
5  "tokens_in": 1847,
6  "tokens_out": 423,
7  "latency_ms": 2341,
8  "success": true,
9  "cost_usd": 0.02
10}

Field	Description
`device_id`	Random anonymous ID (not fingerprintable)
`task_type`	Inferred from token patterns, NOT prompt content
`model`	Which model handled the request
`tokens_in/out`	Token counts (not content)
`latency_ms`	Request latency
`success`	Whether the request succeeded
`cost_usd`	Estimated cost
`timestamp`	ISO 8601 timestamp of the request

What We NEVER Collect

❌ Your prompts
❌ Model responses
❌ File paths or contents
❌ API keys
❌ Your identity or location
❌ Anything that could identify you or your project

Task Type Inference

Task types are inferred from request characteristics (token counts, ratios) — never from prompt content:

quick_task — Short input/output (< 500 tokens)
code_review — Medium-long input, medium output
generation — High output/input ratio
classification — Low output/input ratio
long_context — Input > 10,000 tokens
content_generation — Output > 1,000 tokens
tool_use — Request includes tool calls
general — Default classification

Verify What's Sent

You can audit telemetry before it's sent:

1# See payloads before they're sent
2relayplane-proxy --audit
3
4# Run fully offline (no telemetry at all)
5relayplane-proxy --offline

Opt Out

1# Disable telemetry
2relayplane-proxy telemetry off
3
4# Check status
5relayplane-proxy telemetry status
6
7# Re-enable
8relayplane-proxy telemetry on

Why We Collect This

Anonymous telemetry helps us:

Improve routing decisions (which models work best for which task types)
Track aggregate cost savings across the network
Identify performance issues

Every user (free or paid) contributes to making routing smarter for everyone.

Open Source: You can inspect the telemetry code yourself at github.com/RelayPlane/proxy