Simple, Transparent Pricing

Every request is billed dynamically, with the metric chosen to match each task: resolution × steps for images, characters for speech, tokens for embeddings, duration with optional resolution for video, hours for transcription, input resolution for OCR, and per-image rates for background removal and upscaling. There are no subscriptions, no monthly minimums, and no hidden fees — you fund a prepaid balance and each successful inference deducts its exact cost. Before any job, you can call the matching /price endpoint to preview the precise cost for the model and parameters you plan to use.

Yes. Every new account receives $5 in free credits the moment you sign up — no credit card, no upfront commitment. That balance is enough to test most models extensively, generate hundreds of images, transcribe several hours of video, or prototype a complete AI pipeline. Your account starts on the Basic tier with conservative rate limits designed for testing; making any payment upgrades you to Premium with no waiting period.

Inference is routed through a globally distributed GPU network rather than concentrated in a few hyperscale data centers, which removes most of the infrastructure markup baked into traditional cloud pricing. We also serve highly optimized open-source models — many of them quantized (INT8, FP8, NF4) and distilled — so each request uses fewer GPU seconds without sacrificing output quality. The combined effect can deliver up to 20× lower inference cost for comparable workloads.

deAPI uses Stripe for secure card payments and supported local methods. You can either make one-off top-ups (with preset amounts of $10, $25, or $50) or enable automatic top-ups, which recharge your balance whenever it drops below $2 — perfect for production workloads that can't afford to fail mid-job. For B2B customers needing custom invoices, larger commitments, or tailored billing terms, our team arranges individual agreements; just reach out to support.

The Basic tier offers conservative rate limits (typically 1–10 RPM depending on the endpoint) ideal for testing. The moment you make any payment via Stripe, your account upgrades to Premium with 300 RPM across all endpoints and unlimited daily requests — instantly, with no application process. For high-volume production needs beyond Premium, dedicated capacity, or enterprise terms, our team can set up bespoke arrangements with volume discounts.

Audio transcription is billed per hour of audio processed, starting at $0.021 per hour — a 1-minute voice memo costs roughly $0.0004, a 30-minute podcast episode around $0.012, and a 2-hour audiobook chapter about $0.04. The per-hour rate is flat: there's no surcharge for multiple speakers, accents, background noise, or long recordings.

Upload MP3, OGG or FLAC files up to 20 MB — enough for most podcasts, interviews, and meeting recordings without recompression. Audio-to-Text is upload-only; to transcribe a YouTube, X (Twitter), Twitch, Kick, or TikTok link without downloading it first, use the Video-to-Text endpoint, which shares the same Whisper model and per-hour pricing.

The underlying Whisper Large V3 model offers broad multilingual support with automatic language detection, covering high-resource languages like English, Spanish, French, German, Polish, and Mandarin alongside many lower-resource ones. Word-level accuracy is strong for clean studio audio and remains reliable on noisy real-world content like phone calls, podcasts, and meeting recordings. Mixed-language audio is handled gracefully, with the model adapting per segment.

Yes — every transcription request accepts an include_ts flag that adds timestamps to the transcript, ready for direct conversion into subtitle files (SRT, VTT), chapter markers, or deep links into your audio player. Timestamps don't change the price.

Yes — the /audio/transcriptions/price endpoint accepts either the audio file itself (we probe the real duration) or a bare duration_seconds value, so you can quote a price before the upload ever happens. The calculator above uses exactly that duration-based estimate; for high-volume archives, batch your requests through Premium's 300 RPM with webhooks for asynchronous processing.