Pricing
Packs never expire and bigger packs include bonus credits. Failed generations are refunded. Prices below are what your agent sees from vokox models.
Per-model prices
| Model | Tier | Credits | Good for |
|---|---|---|---|
| Video | |||
| wan-2.2-fastWan 2.2 Ultra Fast 480p | fast | 3 / s | drafts, GIF bases, previews |
| wan-2.2-fast-720pWan 2.2 Ultra Fast 720p | fast | 5 / s | cheapest usable 720p |
| ltx-2-fastLTX-2 Fast | hq | 8 / s | fast, native audio, long clips |
| hailuo-2.3Hailuo 2.3 | hq | 9 / s | strong motion and physics |
| seedance-2-fastSeedance 2.0 Fast | hq | 10 / s | multi-reference, lip-sync, best value for talking heads |
| wan-2.5Wan 2.5 | hq | 12 / s | native audio, stable characters |
| seedance-2Seedance 2.0 | premium | 16 / s | multi-shot, references for face/voice/video, cinematic |
| kling-3-stdKling 3.0 Standard | premium | 18 / s | people, motion, multi-shot |
| veo-3.1-liteVeo 3.1 Lite | premium | 12 / s | cheapest Veo: realism and dialogue on a budget |
| veo-3.1-fastVeo 3.1 Fast | premium | 30 / s | dialogue with lip-sync and SFX, realism |
| kling-3-proKling 3.0 Pro | premium | 45 / s | top motion quality |
| veo-3.1Veo 3.1 | premium | 80 / s | flagship realism, use only when the client asks |
| Image | |||
| z-imageZ-Image Turbo | fast | 2 / image | drafts, thumbnails, sticker bases |
| flux-2-kleinFLUX 2 Klein | fast | 3 / image | fast, good typography |
| qwen-imageQwen-Image | hq | 6 / image | text rendering, edits |
| seedream-4.5Seedream 4.5 | hq | 8 / image | photoreal people and products |
| nano-banana-2Nano Banana 2 | hq | 10 / image | best edits and consistency with references |
| gpt-image-2GPT Image 2 | premium | 12 / image | instruction following, UGC photo look |
| nano-banana-proNano Banana Pro | premium | 30 / image | top quality, 4K, complex scenes |
| GIF | |||
| gif-loopGIF loop (Wan 2.2 480p + ffmpeg) | fast | 20 flat | first frame = last frame for seamless loops; stickers, reactions |
| Music | |||
| lyria-3.5Lyria 3.5 | hq | 15 / track | licensed background music, prompt = genre + mood + tempo |
| stable-audio-2.5Stable Audio 2.5 | hq | 35 / track | ambient, SFX beds, longer tracks |
| Voice | |||
| kokoroKokoro | fast | 1 / 1k chars | English narration at near-zero cost |
| minimax-ttsMiniMax Speech 2.6 Turbo | hq | 10 / 1k chars | good Russian, 30+ languages, emotion control |
| eleven-v3ElevenLabs v3 | premium | 20 / 1k chars | expressive, emotion tags, voice cloning later |
Worked examples
1 product image, 4 variants
32 credits
20 s UGC ad with voice
≈ 240 credits
30 s talking head
≈ 330 credits