CONTINUE OPEN SOURCE
ROUTING ACTIVE
CONTINUE INTEGRATION
3M+ VS CODE INSTALLSOPEN SOURCE

RelayPlane
+ Continue
Save 50%

Continue is the open-source AI coding assistant with 3M+ VS Code installs. Route its LLM calls through RelayPlane for cost tracking and intelligent model routing.

$npx @relayplane/proxy --port 4801
CONTINUE SESSION LOGROUTING
[11:04:01] Tab autocomplete -> haiku
[11:04:02] Tab autocomplete -> haiku
[11:04:05] Explain code block -> haiku
[11:04:07] Chat: refactor auth -> sonnet
[11:04:09] Fix type error -> haiku
[11:04:12] Chat: system design -> opus
[11:04:15] Write unit tests -> haiku
✓ Session complete7 calls · $0.27 (was $1.68)
ALL OPUS$15.00/1M
WITH RELAYPLANEavg $0.85/1M
// ABOUT CONTINUE

The Open-Source AI Coding Assistant

Continue is the most popular open-source AI coding extension, with 3M+ VS Code installs. It supports chat, tab autocomplete, and inline edits through a fully configurable provider system.

Continue connects to any OpenAI-compatible endpoint via apiBase in its config. Set that to RelayPlane and every model request gets cost-tracked and intelligently routed.

TYPICAL CONTINUE SESSION COSTS
Light coding (30 calls)
$3.60$1.80
Active session (100 calls)
$12.00$6.00
Heavy use (250 calls)
$30.00$15.00
MONTHLY (heavy use)
$660+$330
3M+
VS Code installs
50%
Average cost reduction
<1ms
Routing decision latency
// QUICK START

Two Steps to Start Saving

Works with Continue's built-in provider config. No extension changes required.

~/projects/my-project
# Step 1: Start the RelayPlane proxy
npx @relayplane/proxy --port 4801
# Step 2: Edit ~/.continue/config.json
{
  "models": [
    {
      "title": "RelayPlane Auto",
      "provider": "openai",
      "model": "relayplane:auto",
      "apiBase": "http://localhost:4801/v1",
      "apiKey": "your-api-key"
    }
  ]
}
✓ All Continue requests now route through RelayPlane
// CONFIGURATION

Config Reference

Full config: ~/.continue/config.json

~/.continue/config.json
{
  "models": [
    {
      "title": "RelayPlane Auto",
      "provider": "openai",
      "model": "relayplane:auto",
      "apiBase": "http://localhost:4801/v1",
      "apiKey": "your-api-key"
    },
    {
      "title": "RelayPlane Fast",
      "provider": "openai",
      "model": "rp:fast",
      "apiBase": "http://localhost:4801/v1",
      "apiKey": "your-api-key"
    },
    {
      "title": "Claude Sonnet (via RelayPlane)",
      "provider": "openai",
      "model": "claude-sonnet-4-6",
      "apiBase": "http://localhost:4801/v1",
      "apiKey": "your-api-key"
    }
  ],
  "tabAutocompleteModel": {
    "title": "RelayPlane Fast",
    "provider": "openai",
    "model": "rp:fast",
    "apiBase": "http://localhost:4801/v1",
    "apiKey": "your-api-key"
  }
}

model: relayplane:auto

Smart routing mode. Analyzes prompt complexity and routes to the optimal model automatically.

model: rp:fast

Always routes to the fastest, cheapest model. Ideal for tab autocomplete where latency matters.

tabAutocompleteModel

Set this separately to use a fast model for autocomplete while using smarter routing for chat.

provider: openai

Use the openai provider in Continue. RelayPlane exposes a standard OpenAI-compatible API.

// HOW IT WORKS

Transparent Proxy Architecture

01

Continue Makes API Call

POST /v1/chat/completions

Continue sends requests to the configured apiBase. With RelayPlane set, calls go through the local proxy.

02

RelayPlane Routes

-> claude-3-5-haiku

Analyzes prompt complexity. Tab autocomplete and simple questions go to Haiku. Chat and refactors go to Sonnet or Opus.

03

Response Streams Back

<- SSE stream

RelayPlane forwards to the optimal model and streams the response back to Continue. Completely transparent.

// ROUTING MODES

Choose Your Strategy

DEFAULT

Smart Routing

relayplane:auto

Infers task type from prompt. Tab completions go to Haiku. Chat and complex edits go to Sonnet or Opus.

autocomplete -> haiku
chat -> sonnet
SPEED

Fast Mode

rp:fast

Always routes to the lowest-latency model. Best for tab autocomplete.

everything -> haiku
# lowest latency
QUALITY

Quality Priority

relayplane:quality

Routes to the best model for each task. Maximum quality, higher cost.

everything -> opus
# full quality mode
// BENEFITS

What You Get

RelayPlane adds intelligent routing and observability to every Continue request.

Per-Request Cost Tracking

relayplane stats --days 7

See exactly what each session costs

relayplane stats --breakdown

Cost by model, by task type, by hour

Tab Autocomplete Optimization

model: "rp:fast"

Dedicated fast model for tab completions

model: "relayplane:auto"

Smarter routing for chat messages

Local-First Privacy

~/.relayplane/data.db

All logs stored locally in SQLite

telemetry: off (default)

No data sent anywhere without opt-in

Multi-Model Support

claude-sonnet-4-6

Use specific models by name via RelayPlane

provider: openai (standard)

No special Continue plugin needed

// TROUBLESHOOTING

Common Issues

Proxy not running?

Start it with verbose mode to see what is happening:

npx @relayplane/proxy --port 4801 -v

Continue not routing through proxy?

Check that apiBase is set correctly in ~/.continue/config.json:

"apiBase": "http://localhost:4801/v1"

How do I verify routing is working?

Check the stats endpoint while Continue is active:

curl http://localhost:4801/control/stats

Getting authentication errors?

The apiKey in config.json is passed through to the proxy. Make sure it matches your provider key:

export ANTHROPIC_API_KEY="sk-ant-..."
# apiKey in config.json should match or be "any" (proxy handles auth)

Tab autocomplete is slow?

Set tabAutocompleteModel to use the rp:fast mode for lower latency:

"tabAutocompleteModel": {
  "model": "rp:fast",
  "apiBase": "http://localhost:4801/v1"
}

Start Saving Today

One config change. No extension updates. Instant cost reduction in Continue.

100% OPEN SOURCEMIT LICENSECONTINUE COMPATIBLE