/cli and products

OpenAI ChatGPT — Plus $20 with GPT-6 Astra; Pro from $100 (5×) or $200 (20×) with Astra Pro reasoning. Free is Luna, not the frontier SKU.

Anthropic's Claude — the leading AI for reasoning, coding, and professional writing. Overview of features, pricing, strengths, courses, and industry-specific use cases.

Cursor — the AI-native code editor built on VS Code. Cloud agents, Origin code hosting, self-hosted machines, Pro+/Ultra individual tiers, and a Grok integration alongside frontier-model chat.

Google's Gemini AI — deep Workspace integration, multimodal, and a flash-cadence model line. Current text flagship on Google's site is Gemini 3.8 Flash (Sep 2026).

DeepSeek — high-performance AI models at a fraction of frontier cost. Current API line is deepseek-flash (V4.1 Flash, retired from V4 Pro 14 Sep 2026). Access via US vendors to keep data off Chinese servers.

GitHub Copilot — AI pair programming by GitHub/Microsoft. Inline completions, Copilot app, CLI, and a model router that ships GPT-6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, and others in one plan.

xAI Grok — current text flagship is Grok 4.6 (API grok-4.6). Token prices from docs.x.ai. Real-time X search is a tool, not the weights.

Aider — AI pair programming in your terminal. Repo-aware, maps your codebase, auto-commits with sensible messages, works with Claude / DeepSeek / OpenAI / local LLMs. Apache-2.0.

Fireworks AI — fast US-based inference + training for open models. Serverless per-token, on-demand GPU, and a Training API (managed + serverless). SOC 2 + HIPAA.

n8n — fair-code workflow automation. Visual canvas for AI agents and business processes, with JavaScript/Python code nodes, 500+ integrations, self-host or managed cloud.

Perplexity — the AI answer engine. Consumer plans run Pro $20 / Max $200 on top of orchestrating many frontier models. The API is splitting: Sonar deprecates 27 Sep 2026 → Agent API.

Together AI — US-based inference + training platform for open-source models. Serverless per-token, dedicated endpoints, fine-tuning, GPU clusters. Hosts Kimi K3, DeepSeek V4, GLM-5.x, MiniMax M3, Qwen, Llama.