👁 Image
TokenFlow.AI 0.8.1

<p align="center"> <img src="https://github.com/AndrewClements84/TokenFlow.AI/blob/master/assets/logo.png?raw=true" alt="TokenFlow.AI" width="500"/> </p>

TokenFlow.AI

👁 Build
👁 Docs
👁 codecov
👁 NuGet Version
👁 NuGet Downloads
👁 Buy Me A Coffee

💡 Overview

TokenFlow.AI is a lightweight .NET library for tokenization, chunking, and cost estimation across modern large language models (LLMs) such as OpenAI GPT-4o, Anthropic Claude, and Azure OpenAI.

It provides accurate token counting, intelligent text splitting, cumulative usage tracking, and real-time cost estimation for any AI-driven application.
Now includes CLI utilities, developer documentation, full Flow.AI ecosystem integration, and automated performance benchmarking.

🧩 Key Features

• 🔢 GPT-style token counting for .NET
• 🧱 Smart text chunking with configurable token limits and overlap
• 💰 Real-time cost estimation for prompt and completion usage
• 🧮 TokenUsageTracker — track cumulative token and cost usage across analyses
• 🧩 Unified TokenFlowClient — analyze, chunk, and cost in one API
• ⚙️ CLI utilities (TokenFlow.Tools) — positional arguments for simplicity (tokenflow cost "text" gpt-4o)
• 📘 Developer documentation site — API reference + usage guides via GitHub Pages
• 🧾 Benchmark suite powered by BenchmarkDotNet and integrated with CI
• 🔌 Pluggable tokenizer providers — including OpenAI tiktoken, Claude cl100k_base, and Approx fallback
• 🔗 Flow.AI.Core integration — exposes ITokenFlowProvider for shared usage across Flow.AI ecosystem projects
• 💬 CLI v3.0 alignment — enhanced cost commands, dynamic pricing, and Flow.AI registry integration
• 🧠 Dual targeting for .NET Standard 2.0 and .NET 8.0

🧠 Quick Examples

Model-specific tokenizers:

using TokenFlow.Tokenizers.Factory;

var factory = new TokenizerFactory();
var gptTokenizer = factory.Create("gpt-4o");
var claudeTokenizer = factory.Create("claude-3-opus");

Console.WriteLine($"GPT tokens: {gptTokenizer.CountTokens("Hello world!")}");
Console.WriteLine($"Claude tokens: {claudeTokenizer.CountTokens("Hello world!")}");

Flow.AI.Core Provider Integration:

using Flow.AI.Core.Interfaces;
using TokenFlow.AI.Integration;

ITokenFlowProvider provider = new TokenFlowProvider("gpt-4o-mini");
int tokens = provider.CountTokens("gpt-4o-mini", "Hello Flow.AI!");
Console.WriteLine($"Token count: {tokens}");

💰 CLI Usage (Positional Arguments)

Estimate Token Cost

tokenflow cost "Estimate my token cost" gpt-4o

Analyze Prompt Text

tokenflow analyze "Explain large language models simply." gpt-4o-mini

Compare Multiple Models

tokenflow compare "Summarize this text" gpt-4o gpt-3.5-turbo claude-3.5-sonnet

Count Tokens

tokenflow count "Estimate my token cost"

List Available Models

tokenflow list-models

💡 All CLI commands support positional arguments — text first, model second.
Named flags (--model, --input) will be added in a future developer-UX update.

🧪 Running Benchmarks

dotnet run -c Release --project src/TokenFlow.Tools.Benchmarks

Full benchmark documentation:
See

🧪 Running Tests

dotnet test --no-build --verbosity normal

All unit tests are written in xUnit and run automatically through GitHub Actions.
Code coverage is tracked with Codecov, and the project maintains 100% line and branch coverage across all modules.

📊 Code Coverage by Module

🔗 Flow.AI.Core Integration

TokenFlow.AI fully implements the shared Flow.AI.Core.Interfaces.ITokenFlowProvider interface.
This enables all Flow.AI components — including PromptStream.AI, DataFlow.AI, and ChatFlow.AI —
to perform token counting and cost analysis through a unified provider contract.

TokenFlow.AI serves as the engine layer of the Flow.AI ecosystem, powering all higher-level orchestration frameworks.

🛠️ Roadmap

✅ Completed

• Core interfaces and models (ITokenizer, ICostEstimator, ModelSpec, TokenCountResult)
• Added TokenFlow.Tokenizers with advanced tokenizers (OpenAITikTokenizer, ClaudeTokenizer, ApproxTokenizer)
• Extended TokenizerFactory to handle OpenAI/Claude families ✅
• Added TokenFlow.Tools.Benchmarks for tokenizer performance analysis ✅
• Achieved 100% code coverage across all projects ✅
• CLI v2.1 released with structured automation ✅
• Developer documentation site (API + usage guides) ✅
• Integrated Flow.AI.Core v0.1.0 and implemented ITokenFlowProvider ✅
• Full integration tests and shared registry loading ✅
• v0.6.1 — Performance Regression Tracking integrated with CI ✅
• v0.6.2 — Enhanced Cost Estimator using Flow.AI.Core registry ✅
• v0.7.0 — CLI Alignment & Ecosystem Integration ✅

🌟 Future Goals

• Extend CLI tooling for full Flow.AI ecosystem interoperability
• Implement enhanced Flow.AI shared configuration support
• Add named argument flags (--model, --input) for CLI commands
• Begin PromptStream.AI cockpit integration phase

💬 Contributing

Pull requests are welcome!
If you’d like to contribute to TokenFlow.AI, please read the upcoming CONTRIBUTING.md once published.

🪪 License

Distributed under the MIT License.
See for details.

⭐ If you find TokenFlow.AI useful, please give the repository a star on GitHub!
It helps others discover the project and supports ongoing development.