Video Models
Text- and image-to-video generators with cinematic quality, native audio and budget options, compared by cost per second.
MiniMax H3
The first major open-weight video model with native stereo audio — a 33B omni-modal transformer generating 4–15s clips at up to 2K. #1 on Artificial Analysis image-to-video, #4 on text-to-video, and the cheapest model in the top five at $4.80 per minute.
Seedance 2.5
ByteDance's long-sequence video model — native 30-second single-shot clips, up to 50 multimodal reference assets, phoneme-level lip-sync and one-pass synced audio. Launched July 31, 2026; #3 on Artificial Analysis text-to-video, and the priciest of the leaders at $34.12 per minute.
FLUX 3
BFL's unified multimodal model — video (up to 20s with native audio), image, and action prediction from one set of weights, built on Self-Flow. Video GA as of August 4, 2026.
PixVerse V6
The best free pick for short-form video — multi-shot character consistency, native audio and 20+ cinematic lens controls, with daily free credits.
Kling 3.0
A dependable mid-priced video model — excellent human motion and face consistency, native 4K output and multilingual audio, though it now sits mid-table (#16) on Artificial Analysis text-to-video. Kling 4.0 was announced in late September 2026 but is still in limited preview, so 3.0 remains the version you can buy with an API.
Veo 3.1
Google's cinematic video model with native audio — prized for polished, sound-synced clips, though it has slipped to
Kling 4.0
Preview: Kuaishou's Kling 4.0, announced Sept 28–30, 2026 — 30-second native generation, 10 keyframes, 15 combined references, stereo audio and 10-bit HDR. Only Kling 4.0 Flash is in limited early access; the full model and API are still pending.
Gemini Omni 1.1 Flash
Google's conversational video model — generate, edit and extend 3–10 second clips with native audio by chatting with it. Production-ready since August 27, 2026; tied for #1 on Artificial Analysis image-to-video at $9.12 per minute, #8 on text-to-video.
Wan 3.0
Alibaba's unified video generation model — #1 on Artificial Analysis text-to-video, 30-second single-pass clips, multimodal inputs including documents and web pages, $0.05–$0.20/sec API pricing.
MAGI-2 Preview
Sand.ai's open-source 114B MoE video model — generates 10-second clips with synchronized audio using just 6B active parameters per token. Apache 2.0.
Grok Imagine Video 1.5
xAI's dedicated video generation model — native 1080p, 6–15 seconds with synced audio, image/voice references, built on the Aurora autoregressive engine.
Wan 2.7
Alibaba's flagship video model — 1080p with native audio sync, first/last-frame and multi-scene controls, from the Wan series whose open-source lineage made it the community base.
Seedance 2.0
A multimodal-control video model built for e-commerce and reference-heavy jobs — strong image-to-video fit, motion physics and multi-asset input.
Runway Gen-4.5
The professional's video model — rich creative controls like motion brush and camera moves, built into a mature editorial toolset.
Hailuo 2.3
MiniMax's earlier budget video model — fast turnaround for drafts and high-volume social content. MiniMax now files it under Legacy Models; MiniMax H3 is the newer, higher-ranked option.
Sora 2
OpenAI's video model known for physics realism and synchronized audio, available through ChatGPT and the API.