Does Baidu Qianfan have a free tier?
Yes: since 2025-10-24, first activation automatically grants 1M tokens per model across 17 designated models (valid three months, online inference only); remaining quota shows on each model's detail page.
The widest activation grant here: 1M tokens each on 17 designated models (ERNIE, DeepSeek, Kimi K2, Qwen3 lines) for three months — the longest free runway for comparing models on one account. This page is the BYOK quick answer for Baidu Qianfan: 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 Baidu Qianfan. 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.
Baidu Qianfan-specific notes
The preset host is https://qianfan.baidubce.com/v2 — the version prefix is /v2, not /v1. Keys look like bce-v3/ALTAK-…; paste the whole string. Prompt-cache hits bill at 40% of the input price and show up under cached_tokens in the usage payload.
Yes: since 2025-10-24, first activation automatically grants 1M tokens per model across 17 designated models (valid three months, online inference only); remaining quota shows on each model's detail page.
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.