PRODUCT

One control plane for your
AI request path.

Routiqel brings API access, routing preferences, usage records, and project controls into one developer-focused workspace. This page distinguishes the local MVP from planned deployment work.

LOCAL MVP STATUS

Core workflows run locally with FastAPI and SQLite. Provider forwarding is optional and disabled until you configure credentials.

Local MVP

Unified API gateway

Send OpenAI-compatible chat requests through one authenticated endpoint. Start with a deterministic sandbox, then configure a supported provider connection.

Available in local MVPHosted production service not deployed
01
Local MVP

Routing rules

Choose a primary provider, optional demo fallback, request timeout, and bounded retry count. Rules are stored per project.

Available in local MVPHosted production service not deployed
02
Local MVP

Request observability

Review request status, provider, model, latency, token counts, trace ID, and estimated cost. Prompts are not stored by default.

Available in local MVPHosted production service not deployed
03
Estimated

Cost analytics

See usage and estimated cost from the request events recorded by your local project. Provider prices can vary and estimates are not invoices.

Available in local MVPHosted production service not deployed
04
Local MVP

Budget guardrails

Set a monthly project limit and an alert threshold. Requests that exceed an enabled hard limit are rejected before forwarding.

Available in local MVPHosted production service not deployed
05
Optional

Provider management

Connect supported OpenAI-compatible provider accounts. Credentials are encrypted at rest by the local API and never returned to the browser.

Available in local MVPHosted production service not deployed
06

See the actual request flow.

Use the sandbox without an external provider account, then inspect the request metadata in your workspace.