AI API calls,
smarter and
cheaper.
One API key. 60+ models. Let Basktre automatically pick the best model for each request - cutting your AI costs by up to 40% with no loss in quality.
No prompts stored. No response logs. Ever.
# Get your API key at basktre.dev/dashboard
curl https://api.basktre.dev/v1/chat \
-H "Authorization: Bearer bsk_your_key" \
-H "Content-Type: application/json" \
-d '{
"model": "auto",
"messages": [{ "role": "user", "content": "Summarize this document." }]
}'Set model to "auto". We handle the rest.
Basktre analyses your request - length, complexity, task type - and picks the cheapest model that can do it well. You specify the quality bar, we minimise the cost.
task: summarise
tokens: ~320
quality: standard
Everything you need.
Nothing you don't.
One API key
No need to manage accounts across OpenAI, Anthropic, Google, and more.
Auto routing
Set model to auto and we pick the cheapest capable model for each request.
Pin a model anytime
Specify a single model directly when precision matters.
Zero data retention
Prompts and responses are proxied through and immediately discarded.
Pay as you go
Charged per token. No monthly minimums, no seat fees.
60+ models, one endpoint
Access major frontier and open models through one API.
We see the call.
Never the content.
Basktre is infrastructure. We route your requests - we don't read them, log them, or use them for anything.
Frequently asked.
Be first in.
Basktre is in limited beta. Join the waitlist and we'll reach out with access details as spots open up.
No spam. Just an invite when your spot is ready.