Does Infini-AI have a free tier?
No more free LLM quota (per-token postpaid billing since 2026-03-30; the web playground stays unbilled for now); embedding and rerank APIs are still free.
Hosted open flagships (kimi-k2.6 and friends) from the Tsinghua-spun compute company, with embeddings and rerank APIs still free; note the LLM free era ended in March 2026 and base-tier rate limits are tight (12 RPM / 300 RPD). This page is the BYOK quick answer for Infini-AI: key steps, direct console and pricing links, and the app-side notes that matter. Verified 2026-07-18.
Two links up front: get your key at the official console and check rates on the official pricing page. Prices and free quotas move; the official pages are authoritative.
The factory preset declares 1 modality flag for Infini-AI. The models actually available come from the live catalog fetched in-app — catalogs move fast, and the flag only means the protocol wiring is ready.
| Modality | Used for |
|---|---|
| Text | Continuation · roleplay chat · agent |
The one universal host pitfall: the API host must include its full version prefix (this provider's exact form is in the notes below) — the app never appends /v1 for you.
Infini-AI-specific notes
The preset host is https://cloud.infini-ai.com/maas/v1 — the full prefix is /maas/v1, so keep the /maas segment when entering it by hand. An Anthropic-compatible base lives at https://cloud.infini-ai.com/maas. The default tier is capped at 12 RPM / 300 RPD / 12K TPM; upgrade the service tier if you hit walls.
No more free LLM quota (per-token postpaid billing since 2026-03-30; the web playground stays unbilled for now); embedding and rerank APIs are still free.
It's stored on your device only, under system-level encryption — never uploaded or synced to any Foreverse server. Requests go straight from your phone to the provider's official endpoint with zero markup. To revoke access, delete the key in the provider's console.