Honest, usage-based pricing.
wavHook charges the FAL list price plus a flat 2× markup. No credits, no hidden conversion, no expiring balances. If FAL drops a price, yours drops with it on the next deploy.
Enough to generate one full economy-tier variant pack. No payment method required upfront.
Rolling 24-hour ceiling, in user-facing dollars. Raise the cap in settings once your workflow warrants it.
Pay as you go. Balance never expires, never rolls over into an abstract credit unit.
Rate card
Prices shown are raw FAL cost → your price (2×).
Images
Keyframes and still frames. Most director chat turns fire a handful of these.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Nano Banana 2 Default workhorse — fastest, widest style coverage. | per image | $0.08 | $0.16 |
Nano Banana 2 — text-to-image | per image | $0.08 | $0.16 |
Nano Banana 2 Pro Sharper detail, tighter text rendering. | per image | $0.15 | $0.3 |
Seedream v5 Lite | per image | $0.04 | $0.08 |
Flux Kontext Pro | per image | $0.04 | $0.08 |
Flux Kontext Max | per image | $0.08 | $0.16 |
FLUX LoRA Pro Character LoRA inference (~1MP per image). | per image | $0.04 | $0.08 |
FLUX Dev (img2img) Strength + steps + CFG knobs. Output dims follow input. | per megapixel | $0.03 | $0.06 |
FLUX 2 Edit Multi-ref instruction edit. FAL pre-resizes inputs to 1MP for billing. | per megapixel (input + output) | $0.012 | $0.024 |
FLUX 2 Pro Edit — first MP | first megapixel | $0.03 | $0.06 |
FLUX 2 Pro Edit — additional MP | each additional megapixel | $0.015 | $0.03 |
FLUX 2 Max Edit — first MP | first megapixel | $0.07 | $0.14 |
FLUX 2 Max Edit — additional MP | each additional megapixel | $0.03 | $0.06 |
FLUX Kontext Max (single + multi) 9 aspect ratios incl. 21:9 / 9:21. | per image | $0.08 | $0.16 |
FLUX Kontext LoRA Paste-URL LoRA + match-input resolution. | per megapixel | $0.035 | $0.07 |
Z-Image Turbo (img2img) 6B turbo. Up to 3 LoRAs. | per megapixel | $0.0050 | $0.01 |
Z-Image — prompt expansion surcharge Optional toggle. Adds $0.0025 per request when enabled. | per request | $0.0025 | $0.0050 |
Qwen Image Edit Bilingual EN/ZH single-ref. | per megapixel | $0.03 | $0.06 |
Qwen Image 2 Edit Multi-ref 1–3, prompt-expansion ON by default. | per image | $0.035 | $0.07 |
Wan 2.7 Pro Edit (image) | per image | $0.075 | $0.15 |
Hunyuan Instruct Edit | per megapixel | $0.09 | $0.18 |
Grok Imagine Edit 1K / 2K resolution token; provider auto-revises prompt. | per image | $0.022 | $0.044 |
Video
Beat-synced clips. Variant packs typically use 4–8 of these per variant. Audio-on variants cost more.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Kling V3 Pro Premium tier default. Highest fidelity, slowest queue. | per second | $0.22 | $0.44 |
Kling V3 Pro — with audio | per second | $0.34 | $0.68 |
Kling O3 Pro | per second | $0.11 | $0.22 |
Kling O3 Pro — with audio | per second | $0.17 | $0.34 |
Kling V2.6 Pro Standard tier default. Great quality per dollar. | per second | $0.07 | $0.14 |
Kling V2.6 Pro — with audio | per second | $0.11 | $0.22 |
LTX 2.3 | per second | $0.06 | $0.12 |
Grok Imagine Video 720p. Init-variant fast path. | per second | $0.07 | $0.14 |
PixVerse V6 | per second | $0.05 | $0.1 |
PixVerse V6 — with audio | per second | $0.06 | $0.12 |
ByteDance Seedance 2.0 Fast 720p, audio included free. | per second | $0.25 | $0.5 |
Seedance 2.0 Fast — reference-to-video 60% off when video references are provided. | per second | $0.15 | $0.3 |
ByteDance Seedance 2.0 (Standard) 720p, audio included free. ~25% more expensive than Fast for hero/final renders. | per second | $0.31 | $0.62 |
Seedance 2.0 (Standard) — reference-to-video 60% off when video references are provided. | per second | $0.19 | $0.38 |
Google Veo 3.1 — 720p, no audio Highest-quality Veo tier. T2V / I2V / first-last-frame / R2V / extend. | per second | $0.2 | $0.4 |
Google Veo 3.1 — 720p, audio on | per second | $0.4 | $0.8 |
Google Veo 3.1 — 1080p, no audio | per second | $0.2 | $0.4 |
Google Veo 3.1 — 1080p, audio on | per second | $0.4 | $0.8 |
Google Veo 3.1 Fast — 720p, no audio Faster Veo tier. T2V / I2V / first-last-frame / extend (no R2V in Phase A). | per second | $0.1 | $0.2 |
Google Veo 3.1 Fast — 720p, audio on | per second | $0.15 | $0.3 |
Google Veo 3.1 Fast — 1080p, no audio | per second | $0.1 | $0.2 |
Google Veo 3.1 Fast — 1080p, audio on | per second | $0.15 | $0.3 |
Google Veo 3.1 Lite — 720p, no audio Cheapest Veo tier. T2V / I2V / first-last-frame only (no R2V, no extend). | per second | $0.03 | $0.06 |
Google Veo 3.1 Lite — 720p, audio on | per second | $0.05 | $0.1 |
Google Veo 3.1 Lite — 1080p, no audio | per second | $0.05 | $0.1 |
Google Veo 3.1 Lite — 1080p, audio on | per second | $0.08 | $0.16 |
Wan 2.7 — Edit Video Prompt-driven video-to-video edit (2–10s input, 1080p). | per second | $0.1 | $0.2 |
Kling O3 Pro — Edit Video Premium V2V edit with @Element references. Pricing estimated — verify per-job. | per second | $0.18 | $0.36 |
Happy Horse 720p; 1080p auto-doubles via costMultiplier. | per second | $0.14 | $0.28 |
Happy Horse — Edit 720p; 1080p auto-doubles via costMultiplier. | per second | $0.28 | $0.56 |
Lipsync
Sync a talking head to an audio track. Priced per minute of output video.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Sync Lipsync V2 | per minute | $3.00 | $6.00 |
Sync Lipsync V2 Pro | per minute | $5.00 | $10.00 |
Sync Lipsync V3 Highest fidelity. Premium tier. | per minute | $8.00 | $16.00 |
Sync Lipsync React-1 | per minute | $10.00 | $20.00 |
Kling Lipsync (audio-to-video) | per 5 seconds | $0.01 | $0.02 |
Motion control
Control camera moves, zooms, and pans on an input image.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Kling V3 — motion control | per second | $0.17 | $0.34 |
Kling V2.6 — motion control | per second | $0.07 | $0.14 |
Audio
Voice, music, and sound effects. Billed per generation or per minute of output.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
F5 TTS | per take | $0.02 | $0.04 |
ElevenLabs Sound Effects | per generation | $0.03 | $0.06 |
MiniMax Music v2 | per generation | $0.03 | $0.06 |
Cassette AI Music | per output minute | $0.02 | $0.04 |
Editing & effects
Upscale, background removal, segmentation. Fine-tune existing assets.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Topaz Upscale — Image Up to 24MP. | per image | $0.08 | $0.16 |
ByteDance Upscale — Video | per second | $0.01 | $0.02 |
Pixelcut — Background removal | per image | $0.05 | $0.1 |
Bria — Video background removal | per generation | $0.05 | $0.1 |
SAM 3 — Video segmentation | per 16 frames | $0.01 | $0.02 |
SAM 3 — Image segmentation Sub-cent precision preserved in billing ledger. | per request | $0.0050 | $0.01 |
FAL Object Removal | per generation | $0.02 | $0.04 |
Bria Eraser | per generation | $0.04 | $0.08 |
Pro Character LoRA — Training ~1500 steps per character, ~$3.60 raw cost. | per step (1/10 of a cent) | $0.24 | $0.48 |
Stems
Separate a song into vocal, drums, bass, and other tracks.
| Model | Unit | FAL raw | wavHook |
|---|---|---|---|
Demucs (htdemucs_6s) | per minute of song | $0.02 | $0.04 |
What does one variant actually cost?
A typical beat-synced variant: 5–8 Nano Banana 2 keyframes, 5–8 Kling V2.6 Pro clips (avg 3 seconds each, with audio). Back-of-the- envelope:
Keyframes only, no video phase.
Kling V2.6 Pro, audio on.
Kling V3 Pro, audio on.
Pre-flight cost badges on every generate button show exact estimates before you spend.
Ready to try it?
Sign up gets you $5.00 of free credit — roughly one full economy-tier song pack.
Get started