Available models | Oxen.ai

Home Repositories Models Docs Blog Pricing Login Sign up

Search

Model Library

Try the latest models and share the outputs with your team - all in one place.

New models added every week.

Copyright © 2026 Oxen Labs, Inc., All Rights Reserved

Careers Privacy Policy Terms and Conditions

Model Library

Try the latest models and share the outputs with your team - all in one place.

36 models. New models added every week.

Search Models

Model Types

Fine-tuning

Fine-tunable

7

Modalities

Image to Image

6

Image to Text

1

Image to Video

2

Text to Embeddings

1

Text to Image

5

Text to Text

20

Text to Video

3

Video to Text

1

Video to Video

5

Developers

Mistral

10

OOpenai

6

MMeta

4

Google

3

Black_forest_labs

2

Lightricks

2

Qwen

2

AAlibaba

2

KKling

2

Topazlabs

2

BByteDance

1

FLUX.2 Klein 4B

Black Forest Labs

FLUX.2 Klein 4B is a compact 4 billion parameter text-to-image diffusion model optimized for fast inference and high-quality image generation.

text-to-imageimage-to-image

LTX-2 Pro - 19B

Generates high-res 4K@25FPS videos from image+text, with multi-keyframe control, 3D camera logic, and synced audio. (124 chars)

text-to-videoimage-to-video

google/nano-banana-pro

Generates high-resolution images from text, excels at character and background consistency, style adaptation, and natural language-based image editing.

FLUX.2 Klein 9B

Black Forest Labs

FLUX.2 Klein 9B is a compact 9 billion parameter text-to-image diffusion model optimized for fast inference and high-quality image generation.

text-to-imageimage-to-image

LTX-2 Retake

Multimodal LLM for targeted video editing: regenerate 2-16s segments (video/audio/both) via prompts, preserving motion, lighting, and continuity.

text-to-videovideo-to-video

Qwen Image - 2512

Large vision model excelling in photorealistic human portraits, finer natural textures, superior text rendering (esp. Chinese), and instruction-based image editing.

Qwen-Image-Edit-2511

Performs advanced image edits with bilingual text support, precise style preservation, multi-image and semantic editing, plus native ControlNet for enhanced control.

Gemini 3 Flash

Fast multimodal model with configurable reasoning, strong agentic workflows, long context, and tool use for interactive chat, coding, and complex tasks.

text-to-textimage-to-textvideo-to-text

GPT Image 1.5

Diffusion model for high‑fidelity image generation and editing, with strong prompt adherence, preserved composition and lighting, and adjustable quality controls.

WAN 2.6 - Video to Video

Generates videos from reference videos, maintaining character consistency, with multi-shot narratives, up to 15s duration, and native audio sync.

Kling O1 - Reference to Video

Multimodal video model for reference-guided synthesis, preserving motion, camera, and styles from videos/images. Supports video-to-video, multi-image conditioning.

Kling O1 Edit - Video to Video

Text-guided video-to-video editing that preserves motion and continuity while enabling character swaps, style changes, motion transfer, and scene transformations.

Segment Anything 3 - Video

Topaz Video Upscaler

Professional-grade video upscaling powered by AI, from Topaz Labs.

topazlabs/image-upscale

Professional-grade image upscaling powered by AI, from Topaz Labs.

Seedream 4.0

Delivers ultra-fast, high-resolution image generation, precise natural-language editing, and consistent multi-image output—ideal for creative, batch, or professional workflows.

text-to-imageimage-to-image

openai/gpt-oss-20b

Wan2.2 A14B - Text to Video

Delivers high-fidelity text-to-video synthesis at 480p/720p using dual expert models for scene layout and fine motion detail, ideal for creative production.

Llama 3.2 3B Instruct

Llama 3.1 8B Instruct

mistral-nemo

State-of-the-art Mistral model trained specifically for code tasks.

open-mixtral-8x7b

A 7B sparse Mixture-of-Experts (SMoE). Uses 12.9B active parameters out of 45B total.

o1-mini

o1-mini is a fast, cost-efficient reasoning model tailored to coding, math, and science use cases. The model has 128K context and an October 2023 knowledge cutoff.

open-mistral-7b

A 7B transformer model, fast-deployed and easily customisable.

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

ministral-8b-latest

Powerful model for on-device use cases.

codestral-2405

State-of-the-art Mistral model trained specifically for code tasks.

pixtral-12b

Version-capable small model.

open-mixtral-8x22b

Mixtral 8x22B is currently the most performant open model. A 22B sparse Mixture-of-Experts (SMoE). Uses only 39B active parameters out of 141B.

mistral-small-2409

Cost-efficient, fast, and reliable option for use cases such as translation, summarization, and sentiment analysis.

Gemini 1.5 Flash

Fast, Lightweight Model

mistral-large-2407

Top-tier reasoning for high-complexity tasks, for your most sophisticated needs.

gpt-4o-mini

GPT-4o mini is our most cost-efficient small model that’s smarter and cheaper than GPT-3.5 Turbo, and has vision capabilities. The model has 128K context and an October 2023 knowledge cutoff.

gpt-4o

GPT-4o is our most advanced multimodal model that’s faster and cheaper than GPT-4 Turbo with stronger vision capabilities. The model has 128K context and an October 2023 knowledge cutoff.

o1-preview

o1-preview is our new reasoning model for complex tasks. The model has 128K context and an October 2023 knowledge cutoff.

ministral-3b-latest

Most efficient edge model.