# AI models in Nodaro

> Every image, video and audio model you can run in Nodaro, from Veo, Kling, Seedance and Nano Banana to ElevenLabs and Suno, with what each costs in credits.

Source: https://nodaro.ai/docs/models

Nodaro runs <ModelCount /> AI models in one editor: <ModelCount kind="image" /> image models, <ModelCount kind="video" /> video models and <ModelCount kind="audio" /> audio models. You choose a model in the settings of a generation node, and you pay per run in credits. Every model has its own page with its settings, credit prices and the maker's prompting advice.

## Browse by kind

  - [Image models](https://nodaro.ai/docs/models/image): 
Nano Banana, GPT Image, Flux, Seedream, Imagen, Ideogram, Qwen and more.
  
  - [Video models](https://nodaro.ai/docs/models/video): 
Veo, Kling, Seedance, Hailuo, Wan, Grok Imagine, LTX, Runway and more.
  
  - [Audio models](https://nodaro.ai/docs/models/audio): 
ElevenLabs voices, dialogue, dubbing and sound effects, Whisper transcription, and Suno music.
  

## Which model for which job

The catalog's own recommendations, kept in sync with the product:

- best for typography / logos / text-heavy: Nano Banana Pro, GPT Image 2. Nano Banana Pro for diagrams / complex text; GPT Image 2 for logos and short copy.
- cheapest realistic image: Z-Image, Qwen, Imagen 4 Fast. Z-Image is the cheapest. Qwen / Imagen4 Fast for slightly higher quality.
- highest fidelity image: Nano Banana Pro, Imagen 4 Ultra, Flux 2 Flex. Pick by family preference; all three are premium tiers.
- image edit / restyle: Flux Kontext Pro, Ideogram Remix, Seedream 5 Pro (I2I). Flux Kontext preserves identity; Ideogram Remix is character-aware; Seedream 5 Pro for instruction-based edits (5 Lite is the budget option).
- highest-resolution image: Topaz Image Upscale, Nano Banana Pro, GPT Image 2. Generate at the model's top tier, then Topaz upscale 4x (Topaz's only lever is the 1x/2x/4x factor).
- background removal / cutout: Recraft Remove BG. Cheap, no prompt needed.
- best cinematic video: VEO 3.1 Quality, Kling 3.0, Seedance 2. VEO 3.1 Quality for premium narrative; Kling 3.0 for music-synced motion; Seedance 2 for reference-driven consistency.
- cheap batch video clips: VEO 3.1 Fast, Wan 2.2 Turbo, Bytedance Lite I2V. VEO 3.1 Fast is the best price/quality balance with native audio.
- video with start + end frame: VEO 3.1 Quality, VEO 3.1 Fast, Kling 2.5 Turbo Pro, Hailuo 02 I2V Pro, Hailuo 02 Standard, Seedance 2. All listed support an end frame; VEO uses imageUrls[start, end].
- music / song generation: Suno V6, Suno V6 Wild, Suno V6 Mini, Suno v5.5. V6 is the default flagship; V6 Wild for bolder, less predictable results; V6 Mini when speed matters; v5.5 / v5 / v4 keep their own character. Same price.
- voice over / narration: ElevenLabs v3, ElevenLabs Turbo v2.5. v3 supports [audio tags] for emotion; Turbo is cheaper for plain narration.
- lip-sync a portrait to audio: Kling Avatar Pro, Kling Avatar Standard, InfiniTalk. Pro for best mouth shape; InfiniTalk for resolution control.
- transcription / captions: ElevenLabs STT, Incredibly Fast Whisper, Whisper. Captions need WORD timestamps: ElevenLabs STT (always) or Incredibly Fast Whisper. Plain Whisper returns phrase segments only.
- motion transfer (drive a subject by another video): Kling 2.6 Motion Transfer, Kling 3.0 Motion Transfer. Kling 2.6 base is cheap; Kling 3.0 is premium.

For a longer comparison, with everyday and premium tiers for every kind of job, read [Choosing a model](https://nodaro.ai/docs/guides/choosing-models).

## How model prices work

- **Credits per run.** Each generation costs the model's credit price. Some models have one flat price. Others charge by resolution, duration or quality, and each model page lists every tier.
- **The price is shown first.** A node shows the cost on its **Run** button before you run it.
- **You pay for results.** Credits are reserved when a run starts and charged when it delivers. When a model's safety filter blocks a generation, the reserved credits are released.

Read more in [Credits](https://nodaro.ai/docs/concepts/credits).

## Choose a model in a node

1. Select a generation node, such as [Generate Image](https://nodaro.ai/docs/nodes/image/generate-image) or [Generate Video](https://nodaro.ai/docs/nodes/video/generate-video).
2. In the settings panel, open **Provider** and pick a model. The settings below it change to match the model: aspect ratios, durations, resolutions.
3. To run many shots on one model, drive them from a [List](https://nodaro.ai/docs/nodes/automate/list) into one generation node. The node runs once per item, so there is only one model to set.

## Frequently asked questions

### How many AI models can I use in Nodaro?

Nodaro runs well over a hundred image, video and audio models from makers such as Google, OpenAI, ByteDance, Kuaishou, Alibaba, ElevenLabs and Suno. The model pages list every one, with its credit price.

### How do I choose a model?

Select a generation node and pick a model under Provider in its settings panel. The Choosing a model guide compares the models for each kind of job.

### How is a model's price shown?

Every model has a price in credits per run, which can depend on its resolution, duration or quality setting. The node shows the price on its Run button before you run it.

### Can I use my own API keys instead of credits?

On a self-hosted Community or Business install you add your own provider keys. On Nodaro Cloud, generations use credits.