> ## Documentation Index
> Fetch the complete documentation index at: https://docs.infery.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Vision models

> Every vision model on Infery, grouped by what it takes as input.

Models that read an image or video as input and answer in text, through `POST /v1/chat/completions`.

**13 models.** Grouped by input, because that is the choice you make first — a model that
turns an image into a video is not interchangeable with one that starts from a prompt.

Prices are not listed here: they change, and a stale price is worse than none. See the
[live catalogue](https://infery.ai/models) for current rates, and each model's own page there for its full
parameter schema.

## Image → text (9)

| Model                               | Owner      | Also accepts | Notes                                                                                                                                   |
| ----------------------------------- | ---------- | ------------ | --------------------------------------------------------------------------------------------------------------------------------------- |
| `got-ocr-v2`                        | got-ocr    | —            | GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables… |
| `llava-next`                        | llava-next | —            | Vision                                                                                                                                  |
| `moondream2`                        | moondream  | —            | Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a…      |
| `moondream2-object-detection`       | moondream  | —            | Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a…      |
| `moondream2-point-object-detection` | moondream  | —            | Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a…      |
| `moondream2-visual-query`           | moondream  | —            | Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a…      |
| `nemotron-3-nano-omni-vision`       | nvidia     | —            | Vision reasoning variant of NVIDIA's Nemotron 3 Nano Omni.                                                                              |
| `nemotron-diffusion-vlm`            | nvidia     | —            | Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.                                  |
| `x-ailab-nsfw`                      | x-ailab    | —            | Predict whether an image is NSFW or SFW.                                                                                                |

## Video → text (4)

| Model                        | Owner  | Also accepts | Notes                                                                                                                                 |
| ---------------------------- | ------ | ------------ | ------------------------------------------------------------------------------------------------------------------------------------- |
| `scene-finder`               | infery | —            | Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames. |
| `marlin`                     | marlin | —            | Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?    |
| `marlin-find`                | marlin | —            | Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?    |
| `nemotron-3-nano-omni-video` | nvidia | —            | Video reasoning variant of NVIDIA's Nemotron 3 Nano Omni.                                                                             |