See what Claude Code and Codex actually send to the API — and what each part costs.
-
Updated
Jul 27, 2026 - Python
#
token-counting
Here are 68 public repositories matching this topic...
AI API gateway that ends manual channel switching with smart routing, auto failover, exponential cooldown, multi-URL scheduling, live request monitoring and soft-error detection.
golang ai monitoring load-balancer reverse-proxy gemini openai failover api-proxy cost-control codex smart-routing openai-api anthropic claude-api llm-proxy ai-gateway claude-code token-counting protocol-transform
-
Updated
Aug 11, 2026 - Go
Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.
benchmark proxy gemini openai developer-tools billing gpt observability claude llm llmops anthropic evals openrouter cost-tracking llm-observability token-counting ai-billing billing-integrity reliability-benchmark
-
Updated
Aug 6, 2026 - TypeScript
cli pricing tokens developer-tools cost-estimation cost-calculator ai-tools llm pricing-tool anthropic openrouter token-counting
-
Updated
Jul 26, 2025 - Rust
TokenMap is a desktop app for treemap-based codebase analysis by tokens, size, complexity, hotspots, and refactor priority
-
Updated
Apr 12, 2026 - C#
Code intelligence for agents: find the code that matters and keep your context window and tokens lean.
rust code-navigation tree-sitter mcp code-search lean code-intelligence local-first code-retrieval context-window coding-agents ai-coding model-context-protocol mcp-server codebase-indexing repository-search context-engineering token-counting token-budget token-efficient
-
Updated
Aug 11, 2026 - Rust
🚀 Intelligent Claude Code status line with multi-provider AI support, real-time token counting, and universal model compatibility. Supports Claude (Sonnet 4: 1M, 3.5: 200K), OpenAI (GPT-4.1: 1M, 4o: 128K), Gemini (1.5 Pro: 2M, 2.x: 1M), and xAI Grok (3: 1M, 4: 256K) with verified 2025 context limits.
gemini openai grok claude multi-provider ai-tools status-line context-window claude-code token-counting
-
Updated
Sep 17, 2025 - Shell
A local proxy that converts websites and APIs to clean Markdown. Convert HTML pages, JSON APIs, and dynamic sites. Get token counts for LLM budgeting.
agent markdown cli golang crawler proxy mcp html-to-markdown mitm web-scraping claude markdown-generator local-proxy mitm-proxy llm chatgpt mcp-server claude-integration token-counting
-
Updated
Mar 6, 2026 - Go
Lightweight token tracking, cost management, and budget enforcement for LLM API calls
-
Updated
Feb 17, 2026 - Python
Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.
nlp go golang tokenizer gemini openai llama gpt pure-go tokenization mistral go-library bpe wordpiece huggingface sentencepiece llm tiktoken anthropic token-counting
-
Updated
Jul 11, 2026 - Go
ttok-style token counting for Amazon Bedrock
-
Updated
Apr 14, 2026 - Python
A high-performance, multi-agent observability engine designed for the Model Context Protocol (MCP). It provides a non-blocking, transparent proxy layer that implements deterministic token attribution, real-time context-window alerting, and heuristic-driven static analysis to optimize LLM metadata overhead at scale.
-
Updated
Mar 25, 2026 - Python
Local Docker-first AI traffic proxy and operator console.
ai docker-compose self-hosted cost-control traffic-control cost-optimization ai-security user-control ai-security-tool token-counting docker-ai ai-proxy-service
-
Updated
Jul 11, 2026
Token Optimization for Context Engineers. 4.8 KB WASM. Sub-millisecond. Zero dependencies.
ai zig tokenizer wasm gemini tokens openai grok tokenization bun edge-computing cost-optimization cloudflare-workers vercel llm tiktoken anthropic token-estimation context-engineering token-counting
-
Updated
Aug 11, 2026 - TypeScript
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
rust tree-sitter mcp tui developer-tools claude rag code-context secret-scanning code2prompt repo-to-text context-engineering repo-context-builder token-counting codebase-to-text repo-context
-
Updated
Jul 27, 2026 - Rust
A blazing-fast BPE tokenizer for LLMs. Drop-in tiktoken replacement, 20-80x faster.
python nlp rust fast machine-learning performance ai tokenizer openai gpt pyo3 bpe llm tiktoken token-counting
-
Updated
Feb 23, 2026 - Python
.NET library for accurate token counting, cost calculation, and session-based usage tracking across 12 LLM providers including OpenAI, Anthropic, Google, Azure, and more.
-
Updated
Aug 1, 2026 - C#
Open-source LLM FinOps proxy — track OpenAI, Anthropic (Claude), and Google Gemini costs by feature, team, and customer. Zero code changes. pip install burnlens.
python cli proxy gemini openai developer-tools gpt observability claude finops fastapi llm anthropic cost-tracking llm-observability token-counting ai-cost budget-alerts ai-finops spend-tracking
-
Updated
Aug 11, 2026 - Python
VS Code extension + MCP server that validates prompts, routes to the cheapest LLM, and projects token × turn cost before the call. Cuts Copilot premium-request burn on agent loops.
mcp vscode-extension copilot ai-agents cost-optimization github-copilot llm llm-cost token-counting model-routing github-copilot-cost github-copilot-token-control
-
Updated
Apr 24, 2026 - TypeScript
Audit what your CLAUDE.md actually costs: token weight per file/import/skill, duplicate directives, and a trim list. Offline, report-only, zero deps.
-
Updated
Jul 29, 2026 - Python
Improve this page
Add a description, image, and links to the token-counting topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the token-counting topic, visit your repo's landing page and select "manage topics."