Skip to content
aicoolies logo
Twinny logo

Twinny Pricing

open sourceopen source · MITlast verified August 26, 2026official site ↗
PlanPriceNotes
Open Sourceofficial source ↗$0checked 2026-08-26Free and open-source VS Code extension; runs locally with Ollama, LM Studio, or custom API endpoints

structured from cited official pricing sources: “Twinny is a 100% free and open-source (MIT licensed) AI code completion and chat extension for Visual Studio Code. It runs completely locally with Ollama, LM Studio, or other local inference servers with zero subscription fees or telemetry. Users only incur costs if they optionally configure third-party paid cloud model APIs.”

Self-hosting cost

Twinny is open source under the MIT license. Self-hosting does not add a software license fee, but you still pay for infrastructure, operations, and any external model or API usage.

Free & cheaper Inline Completion

same category, free plan or open-source license

Claude CodeClaude Code is included with Anthropic subscription tiers starting at $20/month for Claude Pro, $100/month for Claude Max (5x), $200/month for Claude Max (20x), and $30/user/month for Claude Team ($25/user/month billed annually). Alternatively, developers can use the CLI via pay-as-you-go Anthropic API keys billed strictly per token consumed.CursorCursor offers a free Hobby tier with core editor access, Composer, and Tab completions. Paid individual plans start with Cursor Pro at $20/month ($16/month billed annually) featuring a $20 third-party model allowance and unlimited Cursor models, followed by Pro+ at $60/month and Ultra at $200/month for high-volume developers. Team plans include Teams Standard at $40/user/month ($32/user/month billed annually) and Teams Premium at $120/user/month (5x usage). Enterprise tier provides custom pricing with SAML SSO and SCIM, and on-demand usage is available for pay-as-you-go model overage.AmpAmp pricing (vendor_documented, as-of 2026-09-17): free Hobby tier with all product features, pay-as-you-go orbs or free own Runners, and BYOK / linked ChatGPT (and other) subscriptions with no Amp token fees or limits on non-Enterprise tiers. Optional Individual plans: Megawatt $20/month and Gigawatt $200/month, each bundling included agent usage and orb minutes (vendor Individual cards describe ~45,000 minutes of orb time). Teams workspaces add sharing and pooled credits at no extra workspace fee; members can sit on Hobby, Megawatt, or Gigawatt. Enterprise is custom (SCIM, audit/network controls, pooled credits, priority support).DevinDevin offers a Free tier for evaluation, a Pro tier at $20/month for individual developers, a high-capacity Max tier at $200/month for power users, and a Teams plan starting at $80/month plus $40/seat/month. Custom Enterprise plans are billed based on Agent Compute Units (ACUs).

FAQ

How much does Twinny cost?

Twinny is a 100% free and open-source (MIT licensed) AI code completion and chat extension for Visual Studio Code. It runs completely locally with Ollama, LM Studio, or other local inference servers with zero subscription fees or telemetry. Users only incur costs if they optionally configure third-party paid cloud model APIs.

Does Twinny have a free plan?

Yes — Twinny is open source and free to use.

Can you self-host Twinny for free?

Twinny is open source under the MIT license. Self-hosting does not add a software license fee, but you still pay for infrastructure, operations, and any external model or API usage.

What are free or cheaper Twinny alternatives?

Claude Code, Cursor, Amp are in the same category with a free plan or open-source license.

pricing is editorial catalog data (last verified August 26, 2026) — vendors change plans; confirm on the official site before you buy. Reuse this data under CC-BY 4.0 via /data.