Platform Pricing Solutions People Docs Log in Request Demo
PRICING No hidden fees. No egress charges. No token markups.

Simple, transparent pricing

Start free. Scale as you go. No surprise bills.

Starter
$0
/month

For teams evaluating inference orchestration

  • Up to 10K inference requests/mo
  • 2 model deployments
  • Single region
  • Community support
  • Basic observability
  • 99.9% SLA
Get Started
Most Popular
Pro
$0.012
per 1K inferences

For teams shipping AI in production

  • Unlimited inference requests
  • Unlimited model deployments
  • Multi-region routing
  • RL-optimized placement
  • Advanced observability & alerting
  • Email + Slack support
  • 99.99% SLA
  • Custom data residency
Start Free Trial
Enterprise
Custom
pricing

For organizations with complex requirements

  • Everything in Pro, plus:
  • Air-gapped on-prem deployment
  • Dedicated Field Deployment Engineers
  • Custom RL policy training
  • SSO / SAML / SCIM
  • Dedicated security review
  • Dedicated account team
  • 99.999% SLA
  • Custom MSA
Talk to Sales
Compare Plans

Full feature breakdown

Everything you need to evaluate. No asterisks, no fine print.

Feature Starter Pro Enterprise
Inference Requests 10K/mo Unlimited Unlimited
Model Deployments 2 Unlimited Unlimited
Regions 1 Multi-region Global + On-prem
RL Routing —
Edge Caching —
Compliance Mesh — Standard Full
FDE Support — —
SLA 99.9% 99.99% 99.999%
Support Channel Community Email + Slack Dedicated + 24/7
Data Residency —
SSO / SAML — —
On-Prem — —
Custom Contracts — —
FAQ

Frequently asked questions

An inference request is a single call to a deployed model through the SpinDynamics API. This includes both synchronous and streaming requests. Batch requests are counted per individual inference within the batch. Internal health checks and model warmup calls are not counted toward your usage.
Yes. You can upgrade or downgrade your plan at any time from the dashboard. Upgrades take effect immediately, and you'll be prorated for the remainder of the billing cycle. Downgrades take effect at the start of your next billing period. No lock-in, no penalties.
Yes. For teams processing more than 10M inferences per month, we offer committed-use discounts of up to 40% off the standard per-inference rate. Contact our sales team to discuss custom pricing based on your projected volume and workload characteristics.
The Starter plan includes up to 10,000 inference requests per month, 2 model deployments, single-region routing, basic observability dashboards, community support via Discord, and a 99.9% SLA. No credit card required to get started. The free tier never expires and is designed to let you fully evaluate SpinDynamics before committing.
Pro plan billing is usage-based. You're charged $0.012 per 1,000 inferences at the end of each billing cycle. You can set spending alerts and hard caps in the dashboard to prevent unexpected charges. We provide real-time cost tracking and daily email digests so you always know exactly what you're spending.
If you exceed 10,000 inference requests on the Starter plan, additional requests will be queued but not dropped. We'll notify you via email and in the dashboard, and you can choose to upgrade to Pro at any time to unlock unlimited requests. We'll never bill you without your explicit consent to upgrade.

Still have questions?

Talk to our team. We'll help you find the right plan for your workload.

Request a Demo Read the Docs →