# Native Audio apps

> 26 native audio models and apps on inference shell.

**URL:** https://inference.sh/apps/tag/native-audio

---

- [Kling Video V4 Flash](https://inference.sh/apps/klingai/video-v4-flash.md) `klingai/video-v4-flash`: $0.094/s at 720p
- [Kling Video V4](https://inference.sh/apps/klingai/video-v4.md) `klingai/video-v4`: $0.157/s at 720p, $0.235/s at 1080p
- [Pika H3 Flex (self-hosted)](https://inference.sh/apps/pika/pika-h3-flex-oss.md) `pika/pika-h3-flex-oss`: GPU time, billed per millisecond
- [Pika H3 Flex Reference to Video](https://inference.sh/apps/pika/pika-h3-flex-reference.md) `pika/pika-h3-flex-reference`: $0.06/sec 480p, $0.12/sec 768p, $0.15/sec 1080p, $0.16/sec 2k, $0.20/sec 4k (output+input video sec). Stems: $0.001/sec
- [Pika H3 Flex](https://inference.sh/apps/pika/pika-h3-flex.md) `pika/pika-h3-flex`: $0.02/sec 480p, $0.04/sec 768p, $0.07/sec 1080p, $0.08/sec 2K, $0.16/sec 4K; stems +$0.001/stem-sec
- [Gemini Omni 1.2 Flash](https://inference.sh/apps/google/gemini-omni-1-2-flash.md) `google/gemini-omni-1-2-flash`: $0.0232/sec 360p, $0.0695/sec 720p, $0.1043/sec 1080p, $0.2085/sec 4K, plus $1.50/M input and $9.00/M thinking tokens
- [H3 Max Turbo](https://inference.sh/apps/falai/minimax-h3-max-turbo.md) `falai/minimax-h3-max-turbo`: $0.025/s 480P, $0.04/s 768P, $0.08/s 1080P
- [FLUX 3 Max](https://inference.sh/apps/falai/flux-3-max.md) `falai/flux-3-max`: $0.17/sec at 720p, $0.29/sec at 1080p
- [Grok Imagine Video 1.5](https://inference.sh/apps/xai/grok-imagine-video-1-5.md) `xai/grok-imagine-video-1-5`: $0.08/sec 480p, $0.14/sec 720p, $0.25/sec 1080p; $0.01/input image
- [Seedance 2.5](https://inference.sh/apps/bytedance/seedance-2-5.md) `bytedance/seedance-2-5`: $6.40–$11.70/M tokens, varies by output resolution and visual input
- [Seedance 2.5 Studio](https://inference.sh/apps/bytedance/seedance-2-5-studio.md) `bytedance/seedance-2-5-studio`: $6.40–$11.70/M tokens, varies by output resolution and visual input
- [FLUX 3 Video](https://inference.sh/apps/bfl/flux-3-video.md) `bfl/flux-3-video`: From $17/sec (HD)
- [MiniMax H3](https://inference.sh/apps/minimax/h3.md) `minimax/h3`: $0.08/sec (768P), $0.13/sec (2K), first 5 images free, +$0.04/extra image
- [Seedance 2.0 Studio Mini](https://inference.sh/apps/bytedance/seedance-2-0-studio-mini.md) `bytedance/seedance-2-0-studio-mini`: from $0.00000277/sec
- [Seedance 2.0 Mini](https://inference.sh/apps/bytedance/seedance-2-0-mini.md) `bytedance/seedance-2-0-mini`: $0.0035/K tokens (text-only), $0.0021/K tokens (visual input)
- [Gemini Omni Flash](https://inference.sh/apps/google/gemini-omni-flash.md) `google/gemini-omni-flash`: $1.00/video
- [Kling Video V3](https://inference.sh/apps/klingai/video-v3.md) `klingai/video-v3`: $0.084-$0.42 per second (std $0.084/s, pro $0.112/s, 4K $0.42/s; +50% with audio)
- [Kling Video V2.6](https://inference.sh/apps/klingai/video-v2-6.md) `klingai/video-v2-6`: $0.21–$1.68/video
- [Seedance 2.0 Studio](https://inference.sh/apps/bytedance/seedance-2-0-studio.md) `bytedance/seedance-2-0-studio`: Token-based: $2.40-$7.70/M tokens (varies by resolution and input type)
- [Seedance 2.0 Studio Fast](https://inference.sh/apps/bytedance/seedance-2-0-studio-fast.md) `bytedance/seedance-2-0-studio-fast`: $0.0033/1K tokens (with visual input), $0.0056/1K tokens (text-only). Tokens = (w*h*fps*(input_s+output_s))/1024
- [Seedance 2.0](https://inference.sh/apps/bytedance/seedance-2-0.md) `bytedance/seedance-2-0`: $2.40-$7.70/M tokens by resolution and visual input
- [Seedance 2.0 Fast](https://inference.sh/apps/bytedance/seedance-2-0-fast.md) `bytedance/seedance-2-0-fast`: $0.0033/1K tokens (with visual input), $0.0056/1K tokens (text-only). Tokens = (w*h*fps*(input_s+output_s))/1024
- [Veo 3.1 Lite](https://inference.sh/apps/google/veo-3-1-lite.md) `google/veo-3-1-lite`: $0.03–$0.05/sec (720p), $0.05–$0.08/sec (1080p)
- [Veo 3.1](https://inference.sh/apps/google/veo-3-1.md) `google/veo-3-1`: $0.20-$0.60/sec, 720p/1080p: $0.20 no audio, $0.40 with audio; 4K: $0.40 no audio, $0.60 with audio
- [Veo 3.1 Fast](https://inference.sh/apps/google/veo-3-1-fast.md) `google/veo-3-1-fast`: $0.08-$0.30/sec; no audio: 720p $0.08, 1080p $0.10, 4K $0.25; audio: 720p $0.10, 1080p $0.12, 4K $0.30
- [Seedance 1.5 Pro](https://inference.sh/apps/bytedance/seedance-1-5-pro.md) `bytedance/seedance-1-5-pro`: $2.40/M tokens w/audio, $1.20/M no-audio; draft 0.6x/0.7x