API · MODELS

The models you can call.

Each card below shows a model your account can call from the API once you're on Pro, Pro Plus, or Ultimate. Use the slug as the model param in your POST /api/v1/generate request. Cost bands show the credit range for that model — a single number where the price is flat. Actual cost depends on the resolution, duration, and audio settings you choose.

Image· 11

Seedream 5.0 ProImage
seedream-5-0-pro

ByteDance's flagship image model: precise masked edits, 1K or 2K output, and up to 10 reference images in one request

COST · 145–289 crbytedance
Wan2.7 ImageImage
wan2-7-image

Alibaba's unified image generator and editor — avatar customization, 9 reference images, and text in 12 languages

COST · 90 cralibaba
Wan2.7 Image ProImage
wan2-7-image-pro

Alibaba pairs an optional thinking pass with 9-image reference grounding

COST · 225 cralibaba
GPT Image 2Image
gpt-image-2

OpenAI's newest image model — up to 16 reference images and native 4K output

COST · 1–1 cropenai
Grok Imagine Image ProImage
grok-imagine-image-pro

Describe an edit in plain English — no masks, no sliders — then export up to 2K across nine aspect ratios

COST · 211–216 crxai
Nano Banana 2Image
nano-banana-2

Google's Gemini 3.1 Flash Image — web-grounded search, 14 reference images, up to 2K output

COST · 207–459 crgoogle
Seedream 5.0 LiteImage
seedream-5-0-lite

Reasoning-first Seedream 5.0 tier, pairing built-in reasoning with live web search for accurate, current images

COST · 106 crbytedance
Kling IMAGE O3Image
kling-image-o3

High-resolution text-to-image and editing with multi-reference consistency

COST · 84–168 crkling-ai
Kling IMAGE 3.0Image
kling-image-3-0

2K image generation from Kling AI, tuned for realistic textures and iterative image-to-image edits

COST · 84 crkling-ai
ViviImage
vivi

The getvivix signature model — instant images in any style

COST · 3 crgetvivix
GPT Image 1.5Image
gpt-image-1-5

OpenAI's image model for text-to-image and editing — three sizes, four quality tiers, up to 16 reference images.

COST · 27–601 cropenai

Video· 13

MiniMax H3Video
minimax-h3

Omni-reference video generation with first/last frame control

COST · 2087–6260 crminimax
Seedance 2.0 MiniVideo
seedance-2-0-mini

The lowest-priced tier of Seedance 2.0 — same 720p ceiling as Fast, native audio and multi-shot generation intact

COST · 750–4500 crbytedance
Seedance 2.0Video
seedance-2-0

Premium multimodal video generation with native audio and cinematic motion

COST · 1050–18000 crbytedance
Seedance 2.0 FastVideo
seedance-2-0-fast

Seedance 2.0, tuned for speed — native audio and multi-shot motion intact, minus the flagship's 1080p tier

COST · 900–5850 crbytedance
Kling VIDEO 3.0 4KVideo
kling-video-3-0-4k

True 4K Kling video in three fixed aspect ratios, with native audio and up to 6-shot sequencing

COST · 1260–12601 crkling-ai
Kling VIDEO O3 4KVideo
kling-video-o3-4k

True 4K output in three aspect ratios with native audio and first/last-frame control, from $0.42/second

COST · 1260–12601 crkling-ai
Wan2.7Video
wan2-7

The first Wan with reference-to-video and video-to-video editing — four modes, native audio, multi-shot scenes

COST · 601–900 cralibaba
Veo 3.1 LiteVideo
veo-3-1-lite

Cost-effective video generation at less than half the price of Veo 3.1 Fast

COST · 151–240 crgoogle
PixVerse V6Video
pixverse-v6

Multi-shot cinematic video generation with native audio, 20+ camera controls, and character consistency

COST · 76–346 crpixverse
Seedance 1.5 ProVideo
seedance-1-5-pro

Native synced audio and video in one generation, with output up to 1080p

COST · 180–780 crbytedance
LTX-2 ProVideo
ltx-2-pro

Cinematic LTX-2 Pro text and image to video generator

COST · 1080–7200 crlightricks
LTX-2 FastVideo
ltx-2-fast

LTX-2's faster, lower-latency tier — 4K, 50fps, and optional synced audio

COST · 720–4801 crlightricks
Veo 3.1 FastVideo
veo-3-1-fast

Google's speed-tuned Veo 3.1 model: generate from a prompt, an image, reference photos, or extend an existing clip

COST · 2401–8400 crgoogle

Need a model that isn't listed?

The getvivix catalog has 100+ models across image, video, voice, lipsync, and avatar generation. The cards above are our curated public set. Specialized or higher-end models (production video, custom voice clones, enterprise-only checkpoints) are unlocked per customer.

Email sales@getvivix.com with the model name, your expected volume, and your use case. We typically reply within 24 hours and can usually unlock new models within a day or two — sometimes with custom pricing tailored to your workload.

Programmatic discovery

Don't hard-code slug lists. Call GET /api/v1/models from your code to get an always-fresh list of what your key has access to, including each model's parameter schema and cost band. That way new models you unlock with us appear in your client without a deploy.

Where to next