AI tool comparison
Perplexity Sonar Pro 2 API vs qmd
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Developer Tools
Perplexity Sonar Pro 2 API
Frontier reasoning meets live web grounding in one API call
100%
Panel ship
—
Community
Paid
Entry
Perplexity Sonar Pro 2 is an API model that combines frontier-level reasoning with real-time web grounding, supporting up to 200K context tokens. It's designed for developers who need current, cited information without managing their own search infrastructure. Pricing starts at $3 per million input tokens.
Developer Tools
qmd
Local doc search engine with BM25 + vectors + LLM re-ranking — by Shopify's CEO
50%
Panel ship
—
Community
Free
Entry
qmd is a lightweight local search engine built by Tobi Luetke, CEO of Shopify, for indexing and querying personal knowledge bases, documentation, and meeting notes — entirely offline. It combines three retrieval approaches in a single pipeline: BM25 full-text search for exact keyword matches, vector semantic search via ONNX-based embeddings, and LLM re-ranking using GGUF models through node-llama-cpp. All three stages run locally with no cloud dependency. The tool ships in multiple deployment modes: a CLI for ad-hoc queries, a Node.js library for programmatic use, an HTTP service for local API access, and — most useful for AI workflows — a native MCP server that lets Claude Code, Cursor, and similar editors query your local knowledge base directly during coding sessions. The hybrid retrieval approach means it handles both "find the exact error message from last week's standup notes" and "what was our decision about the auth architecture" equally well. What makes this notable beyond its technical approach is provenance: Luetke shipped it as a personal tool he actually uses, not a startup product. The GitHub history shows active iteration and he's been talking about it on X. It's a credible signal of where pragmatic AI-augmented knowledge management is heading for technical users who prefer local-first tools.
Reviewer scorecard
“The primitive here is clean: LLM inference with search grounding baked in at the API layer, so you're not duct-taping a search API to your context window yourself. The DX bet is that developers would rather pay per-token for a pre-grounded model than orchestrate Bing/Google Search APIs plus chunking logic plus citation parsing — that bet is correct for 80% of use cases. At $3/M input tokens with 200K context, this is actually priced for production use, not just demos. The skip scenario is when you need deterministic source control, because you're trusting Perplexity's crawl decisions, not your own.”
“Hybrid BM25 + vector + LLM re-rank is the right architecture for personal knowledge search — each layer catches what the others miss. The MCP server mode is genuinely useful: being able to ask Claude Code 'what did we decide about X last month' against my own notes changes the workflow. MIT licensed and from someone who ships real products.”
“Direct competitors are Bing Grounding in Azure OpenAI and Google Search-grounded Gemini — both backed by hyperscalers with deeper crawl infrastructure. Perplexity's edge is that grounding isn't an add-on here, it's the entire product surface, which means the citation quality and source selection logic is more refined than what you get bolting search onto a foundation model. The scenario where this breaks is enterprise compliance: you have no SLA on what sources get cited, and regulated industries can't ship that. What kills this in 12 months is OpenAI natively shipping SearchGPT with equivalent grounding at the API level, which is already on their roadmap — Perplexity needs to win on citation quality and context fidelity before that lands.”
“This is a well-executed weekend project, not a production tool. It requires GGUF models and manual embedding setup — a meaningful friction barrier for non-technical users. The 'built by a CEO' narrative drives GitHub stars more than the technical differentiation. Obsidian with a local AI plugin gets you here with better UX.”
“The buyer is a developer or technical product team pulling this from a SaaS or enterprise tools budget — a real budget line with a clear value prop of replacing a search API plus LLM orchestration layer. The pricing scales with usage rather than seats, which is correct for an API product, and $3/M input is competitive enough to survive in production workloads. The moat question is the real issue: Perplexity's index and citation pipeline is proprietary, but it's not obviously better than what Google or Microsoft can build into their own model APIs. This business survives if Perplexity becomes the trusted grounding brand before OpenAI or Anthropic make it a checkbox feature — that window is 12-18 months and shrinking.”
“The thesis is falsifiable: by 2027, most production AI applications will require grounded, cited outputs as a baseline — hallucination-free responses won't be a differentiator, they'll be the floor. Sonar Pro 2 is positioned as infrastructure for that world, not a feature. The second-order effect nobody is talking about is that widespread grounded API usage shifts the web's information economy: publishers whose content trains and grounds these models gain leverage they don't currently have, which will force licensing conversations that reshape content distribution. The trend line is the shift from static model knowledge to real-time retrieval-augmented generation in production apps — Perplexity is on-time, not early, but their grounding quality is ahead of the commodity curve. If OpenAI ships native grounding at parity pricing, this thesis collapses to a niche play.”
“The pattern here — local hybrid retrieval as an MCP server feeding into AI coding agents — will be ubiquitous in two years. Today it's a technical power-user tool; tomorrow it's how everyone's AI assistant knows the institutional context behind the code. qmd is an early, clean implementation of that pattern.”
“I manage a lot of notes, references, and creative briefs, but the setup friction here — GGUF models, CLI configuration — makes this inaccessible for most creators. The concept is great; the UX needs a front-end before it reaches beyond developers.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.