From prototype to production — transparent pricing, no surprises. All plans include latency-based routing, automatic failover, and full API access.
Starter
Starter
$49/mo
10,000 api requests / month
✓Latency-based routing
✓OpenAI + Anthropic + Groq
✓Automatic failover
✓Cost tracking dashboard
✓Email support
Something went wrong. Try again.
Most Popular
Growth
$149/mo
100,000 api requests / month
✓Everything in Starter
✓Priority routing
✓Lower latency SLA
✓Usage analytics
✓Slack support
Something went wrong. Try again.
Enterprise
Enterprise
$499/mo
Unlimited api requests / month
✓Everything in Growth
✓Dedicated capacity
✓99.9% uptime SLA
✓Custom rate limits
✓Onboarding + white-glove support
Something went wrong. Try again.
Common Questions
What counts as an API request?
Every call to /api/infer counts as one request, regardless of how many tokens are in the prompt or response. Failover attempts that don't reach a provider don't count.
What happens if I exceed my plan limit?
We'll notify you and optionally slow traffic rather than cutting you off. You can upgrade mid-cycle and the change takes effect immediately.
Can I switch plans later?
Yes. Upgrade or downgrade at any time from your dashboard. Upgrades take effect immediately; downgrades apply at the start of the next billing cycle.
Is there a free trial?
The Starter plan is available for 14 days free before charging. No credit card required to start.
What payment methods do you accept?
All major credit and debit cards via Stripe. Enterprise customers can request invoicing.
Do you offer annual billing?
Yes — switch to annual in the checkout flow and save 20%. All tiers are available on annual plans.