Plans for Everybody
Bring your own keys and use Fabric free, or buy credits to use every Fabric model — metered by usage, the right model for every task. Go Enterprise for air-gapped deployment.
Get work done across Fabric Small, Medium, Large, and XLarge — the right model for every task. Pay only for what you use.
Example costs are typical, on Fabric Medium; Fabric Large is priced higher. 1 credit = $1 of usage.
Air-gapped or on-premise deployment, zero data retention, and dedicated support — your code never leaves infrastructure you control.
Air-gapped / on-premise deployment
All Fabric models, metered by credits
Dedicated account management
Custom fine-tuned model
SAML/OIDC SSO
Role-based access control
AI code tracking & audit logs
Tier 1 priority support
Compare Plans
| Feature | Buy credits | Enterprise |
|---|---|---|
| Transparent AI reasoning | | |
| BYOK (any API key) | | |
| Model agnostic | | |
| Fabric Medium (metered by credits)1 | | |
| Fabric Large (metered by credits)2 | | |
| Zero data logging | | |
| Shared chats & rules | | |
| GUI + Terminal + CLI | Coming soon | Coming soon |
| Hosted cloud access | | |
| Centralized billing dashboard | | |
| Usage analytics | | |
| API automation | | |
| RBAC | — | Coming soon |
| SSO (SAML/OIDC) | — | Coming soon |
| Custom fine-tuned models | — | Coming soon |
| Air-gapped deployment | — | |
| Audit logs & tracking | — | Coming soon |
| Dedicated support | — | Coming soon |
Intelligent Model Routing
99.2% of frontier accuracy at an 82% reduction in cost. Fabric's patent-pending3 routing sends each task to the right model tier automatically — so you stop overpaying for premium on every request.
Frontier accuracy, without the bill
Hit 99.2% of frontier accuracy at 82% lower cost. Fabric blends Claude and GPT-5 with open-weight models (Qwen, Llama, DeepSeek) in real time, so your team ships at premium quality without the premium invoice.
82% less spend on routine work
Autocomplete, refactors, and boilerplate don't need a 2T-parameter model. Fabric routes them to fast, cheap models automatically — so your budget goes to the tasks that actually move product forward.
You own the cost-quality dial
Tune the mix to your team: max quality for production code, max savings for exploration. Fabric surfaces the usage data so you can set the threshold with confidence, not guesswork.
Frequently Asked Questions
Yes. Bring your own API keys for any provider — OpenAI, Anthropic, Google, Mistral, DeepSeek, or any OpenAI-compatible endpoint — and use Fabric for free. We never train on your data, and chats are not logged on our servers. For a one-time purchase, the $99.99 lifetime license lets you own Fabric outright.
Yes. For $99.99, you can own Fabric outright. The lifetime license includes all updates for the current major version (e.g., all v1.x releases). No token usage is included — bring your own API keys or use free OpenRouter models.
Absolutely. Fabric supports any OpenAI-compatible API endpoint. Bring keys from OpenAI, Anthropic, Google, Mistral, DeepSeek, or any provider. You can also point Fabric at self-hosted models like Qwen, Llama, or any vLLM/Ollama endpoint.
Fabric is model-agnostic. It works with Claude, GPT-4, Gemini, DeepSeek, Qwen, Llama, Mistral, and any model accessible via an OpenAI-compatible API. Enterprise customers can use custom fine-tuned models.
Buy credits and use any Fabric model — 1 credit = $1 of usage. Reply to an email for about $0.02, build a slide deck for $0.50–$1, or a simple web game for $5–$20 (typical, on Fabric Medium; Fabric Large costs more). Monthly plans add bonus credits — $100/mo gives $125 (a 25% bonus) and $500/mo gives $700 (a 40% bonus). Prefer not to pay us at all? Bring your own API keys and use Fabric free.
Yes. Enterprise customers can deploy Fabric fully air-gapped, on-premise, or in a private VPC. Zero data leaves your environment. Fabric supports offline, air-gapped, and sovereign deployment configurations.
Fabric makes AI reasoning transparent — you see how the AI thinks, not just what it outputs. Fabric also supports air-gapped enterprise deployment, BYOK with any model, and is model-agnostic. See our detailed comparison at /compare/cursor.
One-time credit purchases don't expire. Credits from a monthly plan roll over for up to one month, so an occasional light month doesn't waste what you've already paid for.
- 1Fabric Medium — approximate intelligence of OpenAI o3, upgraded as stronger models ship.
- 2Fabric Large — approximate intelligence of Claude Opus 4.1, upgraded as stronger models ship.
- 3Patent Pending — Provisional Patent #63/941,697, inventor Ryan Monsurate.