Labs · Cost calculator
What AI reading costs,
in real prices.
It costs about
$0
≈ ¥0.138 · ≈ 191 credits
Official-channel rate = public list price + 50% service margin
Cost breakdown
Your own key (list price): $0.013
The 5,000 sign-up credits cover this 26× overTokens estimated with a mixed Chinese web-fiction ratio; expect ±15% · Prices captured 2026-07-24 · providers' official pages are authoritative
Sign-up comes with 5,000 credits — enough to try everything this page just priced. The official channel needs no key setup.
Claim 5,000 credits and try itWhere the prices come from, how the math works
Model prices are a build-time snapshot of models.dev public list prices (captured 2026-07-24) — the same source our billing backend syncs, so this page and the real bill aren't two different books. Usage assumptions: one continuation = ~8,000 tokens of context plus 550 tokens out; an evening of chat = a fixed 2,000-token prefix plus history that grows every turn, discounted at the 89.9% cache-hit rate we measured; audiobooks bill per input character, and listening time converts at 250 characters per minute.
The anchor “one continuation ≈ 19 credits” is a measured number from real official-channel billing in the app; the calculator is calibrated against it.
What it can't get right
Tokens are estimates — tokenizers slice Chinese and English differently, and ±15% on the same passage is normal, hence the “≈” on every figure. The cache-hit rate defaults to our measured 89.9%; your real rate depends on how your client organizes requests, and a badly organized one drops to 46.5% (we've been there — the cache calculator has the full story). Promotions, peak/off-peak pricing, and regional differences aren't modeled, and providers can reprice between our snapshots. This page answers “what order of magnitude,” not “what will my invoice say to the cent.”
FAQ
Where do these prices come from?
From a snapshot of public list prices on models.dev (capture date shown on the page, currently 2026-07-24) — the same source our billing backend syncs from. Two bases are shown: the official channel adds a 50% service margin on top of list price (1 credit = $0.0001); bring-your-own-key runs at list price with no markup. Promotions, negotiated rates, and regional pricing are excluded; providers' own pages are authoritative.
How is “one continuation” estimated?
As roughly 8,000 tokens of context in and 550 tokens out (about 300 words of new prose). That calibration matches the app's measured billing: one continuation on DeepSeek V4 Flash costs about 19 credits on the official channel. Tokenizers differ between models, so expect around ±15% — treat results as an order of magnitude, not an invoice.
Is listening to a whole book really free?
The system-TTS tier is genuinely free: it synthesizes on your phone, no API involved, so a 2M-character novel costs nothing. Online AI voices bill per character, and a full 2M-character book runs to tens of dollars — which is why they suit close-listening a single chapter (under $0.15) rather than converting a whole shelf. That math is exactly why the app defaults audiobooks to system TTS.
What do the 5,000 sign-up credits buy?
5,000 credits equal $0.50. On the DeepSeek V4 Flash basis that's about 260 continuations — 80k to 130k characters of new prose — or many evenings of roleplay chat. The official channel needs no key setup; when the grant runs out you can buy credits or switch to your own keys.