Compare LLM API pricing from your terminal. Supports 300+ models across all major providers.
Rich multi-line status bar for Claude Code — model, cost, context, git, rate limits
Stop your AI agent from over-paying for the wrong model. Cost-aware model routing, model-specific prompt optimization (Midjourney, Flux, SD), and pre-flight lint for 80+ generative AI models. Saves 40-70% on agent-driven generation workloads.
Productivity status line for Claude Code — model, cost, context, rate limits, git stats
Helpers for context windows, usage normalization, compaction, and cost estimation.
A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.
Core types and registry utilities for TokenLens (model metadata).
[](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml) [](https://www.npmjs.com/package/ll
The **[OpenAI provider](https://ai-sdk.dev/providers/ai-sdk-providers/openai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the OpenAI chat and completion APIs and embedding model support for the OpenAI embeddings API.
A Claude Code StatusLine hook showing model, cost, context window usage, and git branch
Limit the cost of a GraphQL Query.
Custom metrics for AWS
The **[Perplexity provider](https://ai-sdk.dev/providers/ai-sdk-providers/perplexity)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for Perplexity's Sonar API - a powerful answer engine with real-time web search capabilities.
AWS SDK for JavaScript Cost Explorer Client for Node.js, Browser and React Native
The world's first AI model cost estimation API. Calculate, compare, and optimize AI spending across all major providers.
Claude Code provider selector for Anthropic, Ollama, Ollama Cloud, DeepSeek.com, OpenCode, LM Studio, vLLM, NVIDIA hosted, and self-hosted NIM.
🥇 Cheapest LLM router on RouterArena ($0.05/1K) · 15K+ downloads in 2 weeks · Open-source AI gateway with parallel multi-LLM execution across 47+ providers, ensemble voting, semantic cache, and budget enforcement
The **[Anthropic provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).
The **[Fireworks provider](https://ai-sdk.dev/providers/ai-sdk-providers/fireworks)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and image model support for the [Fireworks](https://fireworks.ai) platform.
OpenCode plugin that recommends the right model cost tier for a development task using a local Ollama classifier.
The **[Google Generative AI provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-generative-ai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Generative AI](https://ai.google/discover/generativeai/)
Playwright Tools for MCP
AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation
The **[Google Vertex provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-vertex)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs.
Ruby port of the Home Care Cost Model reference implementation. Calculates recommended PSW, housekeeping, and nursing hours, private-pay cost, subsidised hours, and the 2026 federal/provincial tax relief stack for Canadian households.
Integrates with models.dev API to provide model validation, cost tracking, and change monitoring for 40+ LLM providers. Validate model names, calculate query costs, and track pricing changes.
Models the cognitive cost of switching between tasks including residual activation, warmup time, context restoration, and practice effects.
A library that uses a scientifically validated model to determine the energetic cost of running up and down hills.
Tracebook is a Rails engine that adds cost tracking, review workflows, and a dashboard UI on top of RubyLLM's Chat and Message models. Features include per-message cost calculation with configurable pricing rules, chat-level approval workflows, and a Hotwire-powered dashboard.
llm_optimizer reduces LLM API costs by up to 80% through semantic caching, intelligent model routing, token pruning, and conversation history summarization. Strictly opt-in and non-invasive.
A Repository-pattern based ORM
Implements Law of Demeter by mapping associated record attributes as own attributes (one-way read-only). Consequently, speeds up SQL queries by removing joins queries between intermediary models, at the cost of slower writes. This is an anti-normalization pattern in favour of actual data-redundancy and faster queries. Use this only as necessary.
Wraps RubyLLM::Chat with input/output contracts, business-rule validation, retry with model escalation on validation failure, pre-flight cost ceilings, and an evaluation framework. Sibling abstraction to RubyLLM::Agent — same niche (reusable class-based prompts), wider contract.
Models situated conceptualization — maintains context frames that shape perception, memory retrieval, and action selection. Tracks context switches with measurable switch costs and familiarity-based discount.
Google Cloud VMware Engine is a fully managed service that lets you run the VMware platform in Google Cloud. VMware Engine provides you with VMware operational continuity so you can benefit from a cloud consumption model and lower your total cost of ownership. VMware Engine also offers on-demand provisioning, pay-as-you-grow, and capacity optimization.
OpenClacky is a 100% open-source (MIT) AI Agent that matches Claude Code on capability at comparable cost. Built on two years of agentic R&D, it ships with a minimal 16-tool core, near-100% prompt cache hit rate, idle-time auto-compression, and BYOK support for any OpenAI-compatible model. A natural-language Skill system lets you create, evolve, and monetize agent capabilities without writing code, plus first-class integrations with Feishu, WeCom, WeChat, Discord, and Telegram.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.