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, output characters 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 processed image, and the price scales with input resolution — there are no monthly fees, no per-seat licensing, and no charges for failed requests. The starting price is $0.00046 for a 1920×1080 (Full HD) image. For reference, a 1080×1080 social-media square comes to $0.00036, a 2000×2000 product photo runs $0.00066, and even a full 4K image (3840×2160) is just $0.00112. That means processing a thousand product photos for an e-commerce catalog typically costs less than a single dollar.

Background removal is powered by Ben2, returning a transparent PNG with a clean alpha channel — no green-screen artifacts, no manual masking. The model handles complex subjects like hair strands, fur, fabric edges, and glass, so it's production-ready for e-commerce packshots, marketing creative, profile portraits, and compositing pipelines. Just send the image and you get back a cutout that drops straight into any design or storefront layout.

The endpoint accepts JPG, JPEG, PNG, GIF, BMP and WebP, with a maximum file size of 10 MB per image. There's no fixed pixel-dimension cap beyond that 10 MB limit, but pricing scales with pixel count — so very large images cost slightly more to process. For most catalog and social-media workflows, sticking to 1080p–2K resolutions keeps costs at a fraction of a cent per image.

Yes. Each request processes one image, but you can fire many requests in parallel — paid (Premium) accounts receive a unified rate-limit of 300 requests per minute with unlimited daily requests, which means you can clear thousands of product photos per hour on a single API key. Combine that with webhook callbacks (an optional HTTPS URL on every request) and you can build a fully asynchronous pipeline that scales without any back-pressure on your application.

The biggest one is e-commerce: turning raw product photography into clean, white-background or transparent assets ready for marketplaces and PDPs. Other heavy users include marketing teams producing social and display creative, portrait apps and ID-photo services, video and design pipelines that need cutouts for compositing, and AI workflows where a clean alpha channel is the prerequisite for downstream steps like upscaling, inpainting, or virtual try-on.