Plans For Every Kind Of Builder
Start free with your own API keys. Scale to Teams when you need collaboration. Go Enterprise for air-gapped deployment and custom models.
Bring your own API keys and build. Full IDE, transparent AI reasoning, all features.
Unlimited token consumption*
Access to free Fabric models
Voice-to-text transcription
Intuitive GUI, Terminal UI, and CLI
Community support
Model agnostic — use any LLM
per user / month
Everything in Individual, plus collaboration tools and managed infrastructure.
Hosted cloud access
API support for automation
Shared chats, commands, and rules
Centralized team billing
Usage analytics and reporting
Role-based access control (coming soon)
SAML/OIDC SSO (coming soon)
Air-gapped deployment, zero data retention, custom fine-tuned models, dedicated support.
Unlimited token consumption
Access to all premium models
Custom fine-tuned model (coming soon)
AI code tracking & audit logs (coming soon)
Role-Based Access Control (coming soon)
SSO+ access control (coming soon)
Tier 1 priority support (coming soon)
Dedicated account management
Air-gapped / on-premise deployment
Compare Plans
| Feature | Individual | Teams | Enterprise |
|---|---|---|---|
| Transparent AI reasoning | | | |
| BYOK (any API key) | | | |
| Model agnostic | | | |
| GUI + Terminal + CLI | Coming soon | Coming soon | Coming soon |
| Voice-to-text | | | |
| Hosted cloud access | — | | |
| Shared chats & rules | — | | |
| Team billing | — | | |
| Usage analytics | — | | |
| RBAC | — | Coming soon | Coming soon |
| SSO (SAML/OIDC) | — | Coming soon | Coming soon |
| Custom fine-tuned models | — | — | Coming soon |
| Air-gapped deployment | — | — | |
| Audit logs & tracking | — | — | Coming soon |
| Dedicated support | — | — | Coming soon |
Intelligent Model Routing
Not every line of code needs a frontier model. Fabric's patented routing algorithms automatically match each task to the right model tier — driving down costs while maintaining accuracy.
A New Cost-Performance Frontier
Fabric's proprietary algorithms blend frontier models (Claude, GPT-5) with cost-effective open-weight alternatives (Qwen, Llama, DeepSeek) in real time. Routine completions route to fast, cheap models. Complex reasoning routes to frontier. You get the accuracy of premium without paying premium on every request.
Up to 70% Lower API Costs
Most coding tasks — autocomplete, simple refactors, boilerplate — don't need a 2T-parameter model. Fabric routes these to smaller, faster models automatically. The result: dramatic cost reduction with negligible accuracy loss on the tasks that matter.
You Control the Mix
Set your own cost-accuracy threshold. Route everything through frontier for maximum quality, or lean into open-weight models for maximum savings. Fabric gives you the dial — and the data to know where to set it.
Need Unlimited API Access?
Power your agentic workflows with All You Can Claw — unlimited access to frontier AI models on dedicated GPUs. OpenAI-compatible API, 60 req/min, no per-token charges. Starting at $14.99/month.
Frequently Asked Questions
Is Fabric really free?
Yes. The Individual plan is free forever with your own API keys (BYOK). You get full access to the IDE, transparent AI reasoning, voice-to-text, and all core features. You only pay your LLM provider directly.
Can I bring my own API key?
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.
What models does Fabric support?
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.
What's included in the Teams plan?
Teams adds hosted cloud infrastructure (no API keys needed), shared chats and rules across your team, centralized billing, usage analytics, RBAC, and SSO. Everything in Individual plus collaboration at scale.
Can Fabric be deployed air-gapped?
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.
How does Fabric compare to Cursor?
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.
Is there a credit or usage-based option?
Yes. In addition to subscription plans, Fabric offers credit packs ($1, $5, $10, $20) for pay-as-you-go access to premium models. Credits never expire.