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.

Pricing scales with resolution and duration, and varies by model. For a 4-second clip at 512×512, LTX-Video 13B starts at $0.005644, LTX-2 19B Distilled FP8 at $0.036186, and LTX-2.3 22B at $0.041212. Even cheaper at lower resolutions and shorter durations — making text-to-video orders of magnitude more affordable than traditional video production. Use the calculator on this page to preview exact pricing for your target dimensions and duration.

LTX-Video 13B is the fastest and most affordable, suitable for prototyping and short clips at lower resolutions. LTX-2 19B Distilled FP8 balances cost and quality and supports longer durations. LTX-2.3 22B is the flagship — best quality, supporting txt2video, img2video, and aud2video tasks, with synchronized audio output baked into the same generation pass. For client-facing content, the 22B model is usually worth the cost increase.

Yes for the larger LTX-2 and LTX-2.3 models — the generated video can ship with synchronized audio in the same single API call, with no second model and no extra charge. That's a meaningful cost advantage versus pipelines that bill video and audio separately. LTX-Video 13B focuses on visual generation, which keeps it the most economical option when you plan to layer your own soundtrack later.

Duration depends on the model and your frames and fps parameters. The 19B and 22B models support longer clips, while the 13B model is optimized for shorter ones. Always read info.limits.min_frames, max_frames, min_fps, and max_fps for the chosen model via the Model Selection endpoint to know the exact bounds. Longer scenes are typically built by chaining multiple generations together using first-frame and last-frame conditioning to keep motion coherent across cuts.

Three practical tactics. First, prototype at a lower resolution and short duration to validate the prompt and motion direction before committing to a higher-quality render. Second, write specific, motion-aware prompts — vague prompts often need re-rolls, which double or triple effective cost. Third, use a fixed seed during prompt iteration so you can compare changes deterministically and preview each render with the /price endpoint before committing.