{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"vscode-bedirt-gpt-token-counter-live","slug":"live-llm-token-counter","name":"Live LLM Token Counter","type":"extension","url":"https://marketplace.visualstudio.com/items?itemName=bedirt.gpt-token-counter-live","page_url":"https://unfragile.ai/live-llm-token-counter","categories":["code-editors"],"tags":["Anthropic","Claude","Counter","Gemini","Google AI","GPT","javascript","Language Model","LLM","OpenAI","plaintext","Token","typescript"],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"vscode-bedirt-gpt-token-counter-live__cap_0","uri":"capability://data.processing.analysis.real.time.local.token.counting.with.live.status.bar.display","name":"real-time local token counting with live status bar display","description":"Counts tokens for selected text or entire open document using embedded local tokenizers (tiktoken for GPT, Anthropic's official tokenizer for Claude, approximation for Gemini) with zero API calls. Updates trigger on every keystroke, selection change, or model family switch, displaying results in VS Code's status bar with customizable template formatting using {count}, {family}, {model}, and {provider} placeholders. No external dependencies or authentication required.","intents":["I need to know token count for my prompt before sending it to an LLM API to estimate costs","I want real-time feedback on how many tokens my selected text consumes as I edit","I need to switch between different model tokenizers (GPT, Claude, Gemini) to compare token usage across providers","I want to display token count in a custom format in my editor status bar"],"best_for":["prompt engineers iterating on LLM prompts in VS Code","developers building LLM applications who need token budgeting visibility","teams evaluating multi-model strategies (OpenAI, Anthropic, Google) with token-aware workflows"],"limitations":["Local tokenizers only — cannot count tokens for custom or proprietary models not in the three supported families","Gemini tokenizer uses crude ~4 chars/token approximation; no precise token boundary detection available for Google AI models","Performance on very large documents (>100k tokens) unknown; real-time updates on every keystroke may cause latency on large files","No project-wide token analysis — only current file and selection supported","Highlighting visual overlays excluded from Output and Debug panes"],"requires":["Visual Studio Code (minimum version unspecified, likely 1.50+)","No API keys or authentication required","Embedded tiktoken library and Anthropic tokenizer (bundled with extension)"],"input_types":["plain text","code (any language supported by VS Code syntax highlighting)","selected text range","entire open document"],"output_types":["integer token count","formatted status bar string (customizable template)","visual token boundary highlighting (optional overlay)"],"categories":["data-processing-analysis","editor-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-bedirt-gpt-token-counter-live__cap_1","uri":"capability://image.visual.visual.token.boundary.highlighting.with.customizable.band.colors","name":"visual token boundary highlighting with customizable band colors","description":"Renders inline visual decorations in the editor that highlight token boundaries using alternating even/odd band colors, making token segmentation visible as you edit. Color customization is provided via a dedicated UI command that opens color pickers for even/odd token bands with hex input and opacity/alpha sliders, with live preview of contrast. Highlighting can be toggled on/off via status bar palette icon or command palette, and is editor-aware (excludes Output/Debug panes).","intents":["I want to visually see where token boundaries fall in my prompt text to understand tokenization patterns","I need to customize the highlighting colors to match my VS Code theme or accessibility needs","I want to toggle token highlighting on/off without changing my model selection"],"best_for":["prompt engineers who need visual feedback on tokenization patterns","developers with accessibility requirements (custom contrast/color settings)","teams using dark/light theme switching who need theme-aware token visualization"],"limitations":["Gemini tokenizer does not support highlighting — only GPT and Claude models can render visual token boundaries","Token boundary detection algorithm is unspecified; accuracy and performance on large selections unknown","Visual overlays add rendering overhead per token; performance impact on documents with >50k tokens not benchmarked","Highlighting is editor-scoped only — cannot be applied to Output, Debug, or other VS Code pane types"],"requires":["Visual Studio Code (minimum version unspecified)","Token highlighting feature available in v1.4.0+","Either GPT or Claude model family selected (Gemini highlighting unavailable)"],"input_types":["selected text range","entire open document"],"output_types":["inline visual decorations (colored bands)","color configuration (hex + alpha values)"],"categories":["image-visual","editor-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-bedirt-gpt-token-counter-live__cap_2","uri":"capability://tool.use.integration.multi.model.tokenizer.switching.with.fallback.chains","name":"multi-model tokenizer switching with fallback chains","description":"Allows users to switch between three pre-configured model families (GPT, Claude, Gemini) via status bar click or command palette, with automatic fallback logic for tokenizer resolution. GPT uses tiktoken with fallback chain: gpt-5 encoding → o200k_base → cl100k_base. Claude uses Anthropic's official tokenizer. Gemini uses approximation (~4 chars/token) when precise tokenizer unavailable. Model selection persists in extension state and updates all displays (status bar, highlighting) instantly.","intents":["I want to compare token counts across different LLM providers (OpenAI, Anthropic, Google) without switching tools","I need to switch my active model tokenizer quickly while editing a prompt","I want the extension to gracefully handle model tokenizer unavailability with sensible fallbacks"],"best_for":["multi-model teams evaluating cost/performance tradeoffs across OpenAI, Anthropic, and Google AI","prompt engineers prototyping the same prompt for multiple LLM providers","developers building LLM applications with provider-agnostic token budgeting"],"limitations":["Only three pre-configured model families supported; custom models or fine-tuned variants cannot be added","GPT fallback chain relies on tiktoken availability; if gpt-5 encoding is unavailable, falls back to o200k_base then cl100k_base (robustness unknown if all fail)","Gemini tokenizer is crude approximation (~4 chars/token); no precise token boundary detection, so highlighting unavailable for Gemini","No per-model configuration (e.g., cannot specify custom tokenizer for a specific GPT variant)"],"requires":["Visual Studio Code","Embedded tiktoken library (for GPT models)","Embedded Anthropic tokenizer (for Claude models)","No API keys or authentication"],"input_types":["model family selection (GPT, Claude, or Gemini)"],"output_types":["active model family identifier","token count using selected tokenizer","visual highlighting (if supported by model family)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-bedirt-gpt-token-counter-live__cap_3","uri":"capability://automation.workflow.customizable.status.bar.token.count.display.with.template.formatting","name":"customizable status bar token count display with template formatting","description":"Displays token count in VS Code's status bar using a customizable template format that supports placeholders: {count} for token count value, {family} or {model} for model family name (GPT, Claude, Gemini), and {provider} for provider identifier (openai, anthropic, gemini). Template configuration is stored in extension settings (exact mechanism unspecified). Status bar element is clickable to switch model families, and includes a palette icon to toggle highlighting.","intents":["I want to display token count in a custom format (e.g., 'Tokens: 1234 [GPT]') in my status bar","I need quick access to model switching from the status bar without opening command palette","I want to see both token count and model family at a glance while editing"],"best_for":["developers who want minimal UI clutter but need token visibility","teams with custom status bar conventions or branding","prompt engineers who frequently switch models and need quick access"],"limitations":["Template customization mechanism is unspecified (likely VS Code settings.json, but exact format unknown)","No conditional formatting (e.g., cannot show different templates based on token count thresholds)","Status bar element is always visible; no option to hide it or move to a different UI location","Template placeholders are limited to {count}, {family}, {model}, {provider}; no custom expressions or functions"],"requires":["Visual Studio Code","Extension settings configuration (exact location/format unknown)"],"input_types":["template string with placeholders"],"output_types":["formatted status bar text","clickable status bar element"],"categories":["automation-workflow","editor-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-bedirt-gpt-token-counter-live__cap_4","uri":"capability://data.processing.analysis.selection.aware.and.document.wide.token.analysis","name":"selection-aware and document-wide token analysis","description":"Analyzes token counts for both selected text ranges and entire open documents independently. When text is selected, the extension counts only the selected range; when no selection is active, it counts the entire document. Token count updates are triggered by selection changes, typing, or model family switches. Both modes use the same underlying tokenizer (GPT, Claude, or Gemini) and display results in the status bar.","intents":["I want to know the token count for just a portion of my prompt (e.g., a specific instruction block)","I need to see the total token count for my entire document to stay within API limits","I want to compare token counts between different sections of my prompt by selecting them"],"best_for":["prompt engineers refining specific sections of long prompts","developers building multi-part prompts (system message + user input + context) who need per-section token budgeting","teams with strict token limits who need granular visibility into prompt composition"],"limitations":["No multi-file or cross-document token analysis — only current open file supported","No project-wide token budgeting or aggregation across multiple files","Selection-based counting does not include metadata or formatting overhead (e.g., if the LLM API adds tokens for message structure, those are not counted)","Real-time updates on every selection change may cause latency on very large documents (>100k tokens)"],"requires":["Visual Studio Code","Active text editor with at least one character"],"input_types":["selected text range (optional)","entire document content"],"output_types":["integer token count for selection","integer token count for document","status bar display (whichever is active)"],"categories":["data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":35,"verified":false,"data_access_risk":"moderate","permissions":["Visual Studio Code (minimum version unspecified, likely 1.50+)","No API keys or authentication required","Embedded tiktoken library and Anthropic tokenizer (bundled with extension)","Visual Studio Code (minimum version unspecified)","Token highlighting feature available in v1.4.0+","Either GPT or Claude model family selected (Gemini highlighting unavailable)","Visual Studio Code","Embedded tiktoken library (for GPT models)","Embedded Anthropic tokenizer (for Claude models)","No API keys or authentication"],"failure_modes":["Local tokenizers only — cannot count tokens for custom or proprietary models not in the three supported families","Gemini tokenizer uses crude ~4 chars/token approximation; no precise token boundary detection available for Google AI models","Performance on very large documents (>100k tokens) unknown; real-time updates on every keystroke may cause latency on large files","No project-wide token analysis — only current file and selection supported","Highlighting visual overlays excluded from Output and Debug panes","Gemini tokenizer does not support highlighting — only GPT and Claude models can render visual token boundaries","Token boundary detection algorithm is unspecified; accuracy and performance on large selections unknown","Visual overlays add rendering overhead per token; performance impact on documents with >50k tokens not benchmarked","Highlighting is editor-scoped only — cannot be applied to Output, Debug, or other VS Code pane types","Only three pre-configured model families supported; custom models or fine-tuned variants cannot be added","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.39,"quality":0.2,"ecosystem":0.35000000000000003,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:34.118Z","last_scraped_at":"2026-05-03T15:20:33.198Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=live-llm-token-counter","compare_url":"https://unfragile.ai/compare?artifact=live-llm-token-counter"}},"signature":"yXHBiJfCn7hj5u0hKTPbJlqt5usZwvp//kwIP0Ea6ynzsQKGgz/bKCsbwnqUoPR7/mIYWS+tYNfhEEvjCyCiAg==","signedAt":"2026-06-19T15:04:24.353Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/live-llm-token-counter","artifact":"https://unfragile.ai/live-llm-token-counter","verify":"https://unfragile.ai/api/v1/verify?slug=live-llm-token-counter","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}