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're billed per generated image based on resolution × inference steps, with the exact rate depending on the model. For a 512×512 image at 4 steps, FLUX.1 schnell starts at $0.00136, FLUX.2 Klein 4B BF16 at $0.00187, and Z-Image-Turbo INT8 at $0.00340. Smaller resolutions and fewer steps cost less; higher quality costs proportionally more. Use the live calculator on this page or the /price endpoint to preview the exact figure before generating.

FLUX.1 schnell is the most economical option and is ideal for fast iteration, social-media assets, and high-volume generation. Z-Image-Turbo INT8 focuses on photorealism with INT8 quantization for production-grade speed at a balanced cost. FLUX.2 Klein 4B BF16 is a unified model handling both text-to-image and multi-reference editing with sub-second inference. Most teams prototype with schnell, then move parts of their pipeline to Z-Image-Turbo or Klein once quality requirements firm up.

Yes. Models available on deAPI ship with commercial-friendly open-source licenses, which means you can integrate generated assets into client projects, paid products, marketplaces, or marketing campaigns. We always recommend reviewing the specific license attached to each model before launching, especially if your use case involves regulated industries or strict content-provenance requirements.

Not always. Each model has a "sweet spot" beyond which extra steps stop improving perceptual quality but keep increasing cost and latency. FLUX.1 schnell is optimized for very low step counts and rarely benefits from going high. FLUX.2 Klein 4B BF16 defaults to 4 steps with fixed guidance for sub-second inference. Z-Image-Turbo supports a broader range and tends to perform best in the lower-to-mid step range. Always start at the model's default, evaluate visually, and only raise steps if a specific subject (typography, fine textures, hands) actually demands it.

Yes — and it's how most production teams operate on deAPI. Pin a model slug and a fixed seed during prompt iteration so you can compare prompt changes deterministically without re-rolling for randomness alone. Use the /price endpoint before each batch to estimate costs upfront for budget tracking. Finally, batch through Premium's 300 RPM limit and use webhooks instead of polling.