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.

You pay per generated video, with cost based on resolution and duration. The starting price is $0.041212 for a 4-second video at 512×512. Other common configurations: a 768×768 talking-avatar at 4s costs $0.045358, a 768×512 short-form social clip at 3s comes in at $0.041230, and a 5s 768×768 personalized outreach video runs about $0.046998. Videos are 2–5 seconds long, with resolutions from 256 px to 768 px on a side.

It generates a lip-synced talking-avatar video conditioned on an audio track plus a text prompt. You provide the audio (the "voice"), an optional first-frame portrait (the "face"), and a prompt describing the scene — the model produces a video where facial motion, mouth shape, and head movement match the audio. It's the building block for AI spokespersons, virtual presenters, sales videos, onboarding messages, and personalized outreach at scale.

The endpoint accepts MP3, WAV, OGG and FLAC with a maximum audio file size of 20 MB. Output videos run 2–5 seconds, which is the sweet spot for short-form content (Reels, TikTok, Stories) and for chunked long-form pipelines where you stitch multiple generations together. Optional first_frame_image and last_frame_image parameters let you anchor the visual identity of the avatar across a sequence.

Yes — and that's the main reason teams use this endpoint. Pair it with Text-to-Speech (Kokoro, Chatterbox, or Qwen3 TTS for voice cloning) to turn a script into audio, and with Text-to-Image (the FLUX family) to generate the portrait. The whole pipeline — script → voice → face → talking video — starts at roughly $0.04 per finished avatar clip, which makes personalized one-to-one video feasible at thousands of recipients per campaign.

The most common workloads are AI spokespersons for product pages and explainer videos, personalized sales and onboarding (the recipient's name spoken in the video), short-form social content (Reels, TikTok, Stories), localized marketing where the same script is rendered in many languages and voices, and virtual presenters for internal training, e-learning, and announcements. Anything where a real on-camera shoot would be slow, expensive, or impractical to personalize.