Neuron Logo
Neuron

Download
Pricing
How Memory Works
X
GitHub
Pricing.

Start free — on managed models or unlimited open-source. Paid tiers add unlimited project indexing and approximate token headroom for entry, mid, and frontier models.

No credit card for free tier·Cancel anytime·BYOK always free and unlimited
$0/monthFree
Limited — Managed Models
  • ~300KTBD entry-tier tokens/month
  • 10 projects indexed (hard cap)
  • Private, standard usage terms
Unlimited — Open Source Models

Runs on provider-hosted free endpoints. Requests may be logged by the provider for security and product improvement. Learn more →

  • Unlimited usage on free, open-source models (e.g. NVIDIA's free endpoint)
  • Provider-hosted — not private by default
Free / BYOK
$0/month

Bring your own key. No credit card required.

  • Unlimited AI requests, bring-your-own-key
  • Project indexing included — embeds using your own configured model
  • No credit card required
Editor License
Launch offer

Separate from the AI usage tiers above — this covers the right to use the Neuron editor itself, annually or once.

LicenseAnnualLifetime — recommended
Non-commercial, unlicensed
Nag reminder shown on launch
$0—
Non-commercial, perpetual
$20/yr$59
Commercial — 1 device
$49/yr$149
Commercial — 2 devices
$69/yr$199
Additional seat
$20/yr$59

Lifetime pricing runs roughly 3x the annual rate — it breaks even against paying annually at around year 3.

Lifetime pricing is a launch offer — available for our first 1,000 users, or through launch — exact cutoff pendingTBD. Anyone who buys in keeps their price forever; the lifetime rate may rise for new buyers once the offer ends.

What a paid license grants: Removes reminders / grants commercial useTBD — copy pending final confirmation, flagged for review.

Coming Soon
Starter
$5/month

More headroom, still on managed models.

  • Unlimited project indexing
  • ~4.1M entry-tier tokens and ~240K mid-tier tokens/month
  • ✕No frontier model access at this tier
  • Framework docs auto-fetch
  • One-click deploy & test
Coming Soon
Pro
$10/month

Frontier models without managing API keys.

  • Everything in Starter
  • Unlimited project indexing
  • Agent Mode + Gather Mode
  • ~4.7M entry, ~640K mid, ~200K frontier tokens/month — mix and match, shared monthly budget
  • Frontier models via Neuron, no key needed
  • Checkpoints, lint auto-detection, priority speed
Coming Soon
Max
$30/month

Our highest limits. For power users who ship fast.

  • Everything in Pro
  • Unlimited project indexing
  • ~10.5M entry, ~1.9M mid, ~910K frontier tokens/month — mix and match, shared monthly budget
  • Early access to new features
  • Priority support

Token allowances are approximate. Usage draws from a shared monthly budget across entry, mid, and frontier models — mix and match freely.

💳
Pay-as-you-go for other frontier models
Past your plan's included token allowance? Top up and keep going on Claude, GPT-5, Gemini, and more — billed at cost, no key management required. Pro and Max only.
🚀
One-click deployment — available on all plans
Deploy to Railway, Render, Vercel, Fly.io, and more directly from Neuron. You're redirected to the provider — we never touch your billing.
RailwayRenderVercelFly.io
Open-source model lane — full disclosure

The unlimited free lane runs on free, open-source models hosted by third-party providers (for example, NVIDIA's free inference endpoint) rather than on our own managed infrastructure. Because these are provider-hosted, free endpoints, the provider — not Neuron — may log requests made through this lane for security monitoring and product improvement, under that provider's own terms.

"Open source" describes the model, not the handling of your data — this lane is not private by default, and we do not recommend it for proprietary or sensitive code. For private usage, use the Limited (Managed Models) lane, a paid tier, or bring your own API key.

Common questions

What is BYOK?
Bring Your Own Key. You can connect your own API keys for Claude, GPT-4o, Gemini, Grok, or any OpenAI-compatible endpoint. BYOK usage is always unlimited on any plan — Neuron never charges for BYOK requests.
What's the difference between the two free lanes?
Limited (Managed Models) runs on our own infrastructure with a small monthly token allowance and one indexed project — private, standard usage terms. Unlimited (Open Source Models) has no usage cap but runs on free, provider-hosted open-source models, which may log requests under the provider's own terms. See the full disclosure on the pricing page for details before using it with sensitive code.
Why do paid tiers use token allowances instead of request counts?
Cost depends on both output tokens and how much context (input) a request carries, not just the number of requests. We bill by output tokens with an approximate monthly allowance per tier, shared across entry, mid, and frontier models — you can mix and match freely rather than being boxed into fixed per-model counts.
What happens if I use up my included token allowance?
On Pro and Max, you can top up with pay-as-you-go pricing for other frontier models — Claude, GPT-5, Gemini, and more — billed at cost, no key management required. Not available on the free tier.
Are Memory and AST Indexing really free?
Yes, forever. Both features run entirely on your machine — no cloud compute, no marginal cost. That's why we can offer them free on every plan, including the free tier.
What is one-click deployment?
From inside Neuron, you can deploy your project to Railway, Render, Vercel, Fly.io, and more with one click. You're redirected to the provider to handle account creation and billing — Neuron never touches your payment details.
What's the difference between a subscription tier and an editor license?
Subscription tiers (Free, Starter, Pro, Max) cover AI usage — token allowances, project indexing, and hosted models. The editor license is separate and covers the right to use the Neuron editor itself: free with periodic reminders if unlicensed and non-commercial, or removable via a one-time or annual license depending on commercial use and device count.
Can I switch plans?
Yes, upgrade or downgrade at any time. Changes take effect immediately and are prorated to the day.

Start free. Upgrade when you need to.

Download Neuron and get unlimited autocomplete, unlimited BYOK requests, Codebase Memory, and AST Code Intelligence — all for free, forever.

Download for free