Your AI agent just got smarter about money.
One API endpoint. Automatic model selection. Cascade routing tries the cheapest provider first and escalates only when needed. Per-request cost tracking. Lightning-settled, OpenAI-compatible.
api.pura.xyz
$ curl -X POST https://api.pura.xyz/v1/chat/completions \
-H "Authorization: Bearer pura_demo" \
-H "Content-Type: application/json" \
-d '{"messages":[{"role":"user","content":"What is backpressure routing?"}]}'click run to send a request through the pura gateway
── DAILY INCOME STATEMENT
Every morning your agent gets this. Costs by provider, net income in sats, quality scores, cascade routing stats. One endpoint: GET /api/income
── HOW IT WORKS
1connectChange your baseURL to api.pura.xyz. Drop-in OpenAI-compatible.→
2routePura picks the best model, escalates with cascade routing if the first answer falls short.→
3trackPer-request cost breakdown, daily spend reports, and budget caps. Lightning funding when credits run out.
// swap your base URL — everything else stays the same
const openai = new OpenAI({ baseURL: "https://api.pura.xyz/v1" });── WHAT PURA REPLACES
x402, AP2, ACP, and TAP are payment authorization rails — they answer whether an agent can pay. Pura sits above them and answers where the payment should go: routing, cost optimization, and capacity-aware flow control on top of any settlement layer.
| Tempo MPP | load balancer | OpenRouter | pura | |
|---|---|---|---|---|
| Model routing | None | Manual | None | Auto by complexity |
| Cost optimization | None | Markup pricing | None | Cascade — cheapest sufficient tier |
| Flow control | Temp MPP | None | None | Backpressure + Boltzmann |
| Capacity signal | None | Server-side | Server-side | On-chain, EWMA-smoothed |
| Completion verification | None | None | None | Dual-signed receipts |
| Settlement | ILP | Stripe | Credit | Lightning |
── GO DEEPER
── SHADOW MODE
See what Pura would do — without changing anything. Install the sidecar and watch.
explore →