Token Budget Intelligence
for GitHub Copilot
Know the cost before you send. A free VS Code extension that counts tokens with real BPE encoders, monitors your context budget in a live sidebar, scores every open tab for relevance, and estimates cost-per-turn across 17 model profiles. Type @tokalator in Copilot Chat to count, optimize, pin, preview, and route. Upgrade to Pro for workspace security scanning and smart model routing, or Enterprise for team analytics, usage dashboards, audit logs, and cost management.
Quick Start
- 1Install Tokalator Pro from VS Code Marketplace.
- 2Open any file and check the sidebar for token budget.
- 3Use @tokalator in Copilot Chat: count, optimize, pin, preview.
Specs
- Encoders
- Claude BPE + o200k_base (OpenAI)
- Models
- 17 profiles: Claude 4.x, GPT-5.x, o3, o4-mini, Gemini 3.x/2.5
- Commands
- 11 @tokalator chat commands
- Scoring
- 5-signal tab relevance (R ∈ [0,1])
Features
BPE Tokenization
Real token counts with Claude BPE and OpenAI o200k_base encoders.
v0.0.1Context Budget Meter
Live sidebar showing token usage vs model context window with Budget Level indicators.
v0.0.1Tab Relevance Scoring
5-signal scoring: language match, import relationships, path similarity, edit recency, diagnostics.
v0.0.1Cost-per-Turn Estimate
Know the dollar cost before you send. Per-MTok pricing for 17 models.
v0.0.117 Model Profiles
Claude Opus/Sonnet/Haiku 4.x, GPT-5.x, o3, o4-mini, Gemini 3.x/2.5 with live pricing.
v0.0.1Next Turn Preview
Project total tokens after your next turn to decide whether to send or restart.
v0.0.1Workspace Security Scan
Detect Sensitive Files (.env, .pem, credentials) and generate deny rules for Claude, Copilot, Cursor.
ProSmart Model Routing
Automatically select the most cost-effective model based on task complexity.
ProTeam Analytics
Usage dashboards, audit logs, cost insights, and spend controls across your organization.
EnterpriseChat Commands
@tokalator /countCount tokens in the active file with real BPE encoding.
@tokalator /budgetShow full context budget: used, remaining, and Budget Level.
@tokalator /breakdownDecompose budget into files, system prompt, instructions, history, Output Reservation.
@tokalator /previewPreview next turn's total token count and estimated cost.
@tokalator /costEstimate cost-per-turn for the current model at current context size.
@tokalator /optimizeClose low-relevance tabs (R < threshold) to free context budget.
@tokalator /pinPin a file to always-include with relevance R = 1.0.
@tokalator /unpinRemove a file from Pinned Files list.
@tokalator /modelSwitch active model profile (17 models with live per-MTok pricing).
@tokalator /scanScan workspace for Sensitive Files and generate AI agent deny rules.
@tokalator /statusShow Context Health, Compaction Point, and session summary.
Pricing
VS Code extension. Token calculator.
- ✓ BPE tokenization
- ✓ Budget meter
- ✓ 6 model profiles
Dashboard, routing, budgets.
- ✓ Usage dashboard
- ✓ Smart routing
- ✓ Budget alerts
Team analytics, SSO, audit logs.
- ✓ Team analytics
- ✓ SSO / SAML
- ✓ Unlimited seats