Pricing
Screen reading runs on-device and never leaves your machine. Add frontier cloud models when you need deeper reasoning — pay only for the tokens you use.
Local
PRIVATE100% private, always on-device
No account required
Cloud
Local privacy + cloud intelligence
Billed €84/yr · Save €24
Pro
Full reasoning, every model, more credits
Billed €204/yr · Save €60
Need more cloud credits? Buy top-up packs at any time — they never expire. See packs ↓
Token top-ups
Credits work across all cloud providers. Larger packs include bonus credits. They never expire and are spent before monthly allowances.
Model library
Local models run on your hardware at zero cost. Cloud models consume token credits from your balance.
New models added regularly. Browse the full catalogue →
Compare plans
Enterprise
On-prem · screen governance · unlimited seats · SSO
Deploy Kyubi fully on-premise for complete data sovereignty — screen captures never leave your network. Define org-wide policies for which applications Kyubi can observe, with a full audit log of every inference request. Enterprise contracts include SSO, SCIM, and volume-discounted token pricing across all providers on a single invoice.
Run the full Kyubi stack on your own infrastructure. Air-gapped installs available for regulated environments where screen data cannot touch external networks.
Your cloud API requests route through isolated infrastructure with a guaranteed throughput SLA — no shared tenancy, no data co-mingling.
Define org-wide policies for which apps and windows Kyubi is permitted to capture. Full audit log of every screen-context request.
One set of provider API keys for your whole org with fine-grained per-team and per-user spend limits.
SAML 2.0 / OIDC single sign-on and automated user provisioning via SCIM. Works with Okta, Entra, and Google Workspace.
Negotiate committed token volumes at discounted rates, unified across all cloud providers on a single invoice.
FAQ
Never. Screen capture is processed on your localy device if you use a local model and is never saved to Kyubi's servers. If you choose to use a cloud model, it goes directly to the model then is deleted Kyubi does not retain a copy.
Kyubi captures the active window or a selected region, sends it to a local vision model (LLaVA 1.6 or Moondream 2) running entirely on your machine, and the model replies. No internet connection is required and no data ever leaves your device.
Cloud model providers (OpenAI, Anthropic, Google, etc.) charge per token — roughly per word processed. When you send a message or a screen capture to a cloud model in Kyubi, the cost is deducted from your credit balance. Included credits refresh each billing period. You can top up manually at any time and those credits never expire.
Included monthly credits do not roll over — they reset each billing period. Manually purchased top-up credits are permanent and never expire. Kyubi always draws from your included credits first before touching your top-up balance.
Any model compatible with Ollama or llama.cpp, Hardware is the main constraint: larger models need more VRAM or Apple unified memory check compatibilaly.
No, we use proprietary infrastructure and do not support bringing your own API keys for cloud providers.
Cloud model requests will be paused until you top up or your next billing period begins. Local models and on-device screen reading are completely unaffected and will keep running regardless of your credit balance.
Yes. Upgrades take effect immediately and are prorated. Downgrades apply at the end of the current billing period so you keep your current features until then.
Always free, always on-device. No account, no cloud required.