Total Savings Generated
$0.0000
Est. cost without Tokenly: $0.0000 across 0 requests
0%
Relative Savings
0%
Token Saved
$0.00
Net Expenditure
Tokens Saved
0
original → optimized
Output Tokens
0
Total generated tokens
Avg Savings / Request
$0.0000
per proxied request
Requests Processed
0
routed via smart model selection
💸 What You'd Pay Each Provider (vs Tokenly)
🎯 Complexity Distribution
📈 Total Spend — Tokenly vs. Standard Providers
🗜️ Tokens Saved Per Day
⚡ Recent Requests
All Requests
Time ↕ Prompt Model Provider Tier Tkns Actual GPT-5 Sonnet Gemini Grok Saved Lat.
Cost Efficiency
0%
Savings vs. Frontier Models (GPT-5/Sonnet)
$0.00
Total Saved
0%
Token Redux
Using Tokenly Proxy
Actual Spend $0.00
Tokens Billed 0
Avg. Latency 0ms
Without Tokenly (Frontier Only)
Hypothetical Spend $0.00
Raw Tokens 0
Frontier Models GPT-5 / Opus
📊 Per-Provider Savings Breakdown (vs your usage)
🚀 Getting Started
🐳
1. Install Docker

Tokenly Core runs in a Docker container to ensure consistent routing logic and model benchmarks. Ensure Docker Desktop is running.

Download Docker
🧩
2. Get Continue.dev

Install the Continue extension in VS Code or JetBrains. This is the recommended way to use Tokenly for coding.

Install Extension
⚙️
3. Select Tokenly

Once the extension is installed and Tokenly is running, simply select "Tokenly" from the model selector dropdown.

tokenly start --ide continue
🌐 Supported Providers & Models

Tokenly supports all major providers and intelligently routes between them based on complexity. Click a provider to see supported models.

OpenAI
Anthropic
Gemini
xAI (Grok)
Meta (Llama)
🛠️ CLI Commands
tokenly setup First Time

Initializes your environment, validates API keys, and creates the persistent configuration in ~/.tokenly/.

tokenly start Daily Use

Launches the local proxy server (port 8001) and the analytics dashboard. Use --port to override.

tokenly dashboard Analytics

Quickly opens this dashboard in your default browser to view your savings and request logs.

tokenly logs Admin

Streams the real-time logs from the proxy service. Useful for debugging connection issues.

💡 Use Cases

Local Development

Build and test AI-powered applications without worrying about high API costs. Tokenly handles the routing to cheaper models for simple tasks.

Benchmarking

Compare how different models perform on your specific prompts using the Benchmark view. See exactly how much you'd pay OpenAI vs Anthropic.

Context Compression

For long conversations or codebases, Tokenly automatically compresses your prompt context to save up to 80% on input tokens.

CI/CD Integration

Run your automated tests through the Tokenly proxy to monitor cost regressions and performance across different model tiers.