Cost Optimization
How RelayPlane saves you money without sacrificing quality.
The Problem
AI coding agents send everything to expensive models. A simple "list files in this directory" costs the same as "architect a distributed system." Most tasks don't need Opus-level reasoning.
Without RelayPlane
- Every request → Opus ($15/MTok)
- Tool calls → Opus
- Simple questions → Opus
- ~$100-300/month typical
With RelayPlane
- All requests → Haiku ($0.25/MTok)
- 60x cheaper per token
- Same API, same tools
- ~$5-20/month typical
How Routing Works
By default, RelayPlane routes all requests to Haiku for maximum cost savings. The proxy tracks task types to help you understand your usage patterns:
| Task Type | Default Model | Cost |
|---|---|---|
| tool_use | Haiku | $0.25/MTok |
| quick_task | Haiku | $0.25/MTok |
| code_review | Haiku | $0.25/MTok |
| generation | Haiku | $0.25/MTok |
| long_context | Haiku | $0.25/MTok |
| general | Haiku | $0.25/MTok |
Why Haiku for everything? Most agent tasks (tool calls, file reads, simple edits) don't need Opus-level reasoning. The proxy optimizes for cost by default. Quality routing with model escalation is coming in a future release.
Typical Results
40-60%
Cost Reduction
~70%
Tasks Routed Down
0ms
Added Latency
View Your Savings
1relayplane-proxy statsExample output:
1📊 Usage Statistics2═══════════════════34 Total requests: 1,2475 Total cost: $42.186 Success rate: 95.3%78 By Model:9 claude-3-5-haiku: 847 requests, $8.1210 claude-sonnet-4: 312 requests, $24.0611 claude-opus-4: 88 requests, $10.001213 By Task Type:14 tool_use: 523 requests, $5.0015 quick_task: 324 requests, $3.1216 code_review: 248 requests, $24.0617 generation: 152 requests, $10.00No Quality Loss: Complex tasks still go to Opus. You only save money on tasks that don't need premium reasoning.
Real-World Example
A typical OpenClaw coding session might look like:
- 50 tool calls (read file, list dir, search) → Haiku
- 15 code reviews/edits → Sonnet
- 3 architecture decisions → Opus
Without RelayPlane: All 68 requests to Opus = ~$15
With RelayPlane: Mixed routing = ~$6