Open-weight models on dedicated GPUs

Unlimited AI.
No surprises.

Unlimited agentic AI from $14.99/month. No per-token billing. No session anxiety. No surprise invoices.

Dedicated
GPU Cluster
256K
Context Window
397B
Parameters (Large)
OpenAI
Compatible API

Two ways to use it

Choose your weapon. Same unlimited plan, same models.

</>

Direct API Access

Drop-in replacement for OpenAI. Works with any client library, framework, or curl command.

# Works with any OpenAI-compatible client
curl https://api.codewithfabric.com/v1/chat/completions \
-H "Authorization: Bearer $KEY" \
-d "{\"model\": \"fabric-small\", ...}"
{ }

Fabric IDE

AI-native coding IDE. Sign in with the same account and your unlimited plan activates automatically.

1
Download Fabric from codewithfabric.com
2
Sign in with your Google account
3
Start coding with unlimited AI

Open-weight models, dedicated infrastructure

fabric-small
Qwen 3.5 35B-A3B
Mixture of Experts
  • 35B total, 3B active parameters
  • Ultra-low latency responses
  • Great for autocomplete, chat, quick tasks
fabric-medium
Qwen 3.5 27B
Dense Architecture
  • 27B dense parameters (all active)
  • Stronger reasoning and code quality
  • Best balance of speed and capability
fabric-large
Qwen 3.5 397B-A17B
512 Experts, 256K Context
  • 397B total, 17B active (MoE)
  • Frontier-class coding performance
  • 256K token context window

Simple pricing

Pick a tier. Use it as much as you want. Cancel anytime.

Small

$14.99/month
Fast, lightweight model for everyday coding tasks
fabric-small
Currently: Qwen 3.5 35B-A3B*
  • ✓Unlimited requests to fabric-small
  • ✓35B parameters, 3B active (MoE)
  • ✓Blazing fast inference
  • ✓OpenAI-compatible API
  • ✓60 requests/minute
Get Started
MOST POPULAR

Medium

$24.99/month
Dense 27B model for complex reasoning and code generation
fabric-small + fabric-medium
Currently: Qwen 3.5 27B + 35B-A3B*
  • ✓Unlimited fabric-small + fabric-medium
  • ✓27B dense parameters
  • ✓Stronger reasoning & code quality
  • ✓OpenAI-compatible API
  • ✓60 requests/minute
Get Started

Large

$100/month
Full 397B frontier model on dedicated GPUs
All fabric models
Currently: Qwen 3.5 397B-A17B + 27B + 35B-A3B*
  • ✓Unlimited access to ALL models
  • ✓397B params, 17B active (512 experts)
  • ✓256K context window
  • ✓Frontier-class coding performance
  • ✓60 requests/minute
Get Started

All plans include Google/Apple/GitHub sign-in. Credit packs available for pay-as-you-go usage on top of any plan.

*We monitor open-source model development and swap out models when new pareto frontiers are achieved. For example, in February 2026 we replaced Devstral 24B with Qwen 3.5 27B. The goal is to always provide higher capability at the same price.

Frequently asked questions

What models are included?

All models run on our dedicated GPU cluster. Small is Qwen 3.5 35B-A3B (mixture of experts, ultra fast). Medium is Qwen 3.5 27B (dense, stronger reasoning). Large is Qwen 3.5 397B-A17B (512 experts, frontier-class). Higher tiers include access to all lower-tier models.

Is the API OpenAI-compatible?

Yes. Point any OpenAI SDK client at our endpoint and it works. curl, Python, TypeScript, Go — whatever you use. Just swap the base URL and API key.

What's the rate limit?

60 requests per minute across all plans. This is per-user, not per-key. For most agentic workflows this is more than enough.

Can I also use the Fabric IDE?

Absolutely. Sign into Fabric with the same account and your unlimited plan just works. Fabric will automatically default to your subscribed model tier.

What if I need more than what's in my tier?

You can upgrade anytime. You can also add credit packs ($1, $5, $10, $20) to access models outside your tier on a pay-per-use basis.

Is there a free tier?

Fabric has a free BYOK (Bring Your Own Key) tier where you use your own API keys. All You Can Claw plans are for people who want a simple, all-inclusive price.

What's the catch?

No catch. We run open-weight models on our own hardware. Low margins, high volume. We believe AI should be a utility, not a luxury.