Icon for Inferbase

Inferbase

Free Trial

AI gateway with policy routing, fallback, guardrails and logs, on your own provider keys or managed models

Inferbase is an AI gateway with an OpenAI-compatible endpoint that picks a model per request from pools and presets you define, with automatic fallback, guardrails, spend caps and request logs. It works with your own provider keys and cloud accounts, where it adds nothing to the token price, or with managed models served through Together, DeepInfra and Novita and paid from prepaid credit.

The free plan includes 5,000 requests a month; Pro is $25/month with 50,000 requests and $10 of managed credit. Inferbase is based in Bengaluru and not yet incorporated.

Pricing: Monthly subscriptions

Pricing Free plan (5,000 requests/month); Pro $25/month
HQ ๐Ÿ‡ฎ๐Ÿ‡ณ India

Data and privacy

Checked 20 November 2026
Data processed
United States (Railway, US West); managed inference on Together, DeepInfra and Novita; own-key requests go to the customer's provider source
Sub-processors
View the list โ†—
US parent company
No

Read from Inferbase's own legal pages. "Not public" means it is not on their site; some providers share it on request.

Screenshot of Inferbase webpage

Work on Inferbase? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →