Models

  • Our catalog features the most popular open-source AI models from developers worldwide, including large language models (LLMs), multimodal, and diffusion models. Try any model in one place—we’ve made it easy for you.
  • To explore and test a model, you can run it on our public endpoint. For production use, fine-tuning, or custom weights, we recommend choosing either: a private endpoint, or a dedicated cloud server.

Gemma-3-27B

Gemma 3 27B — flagship multimodal model from Google DeepMind with 27 billion parameters and maximum performance. It is easy to fine-tune and ideal for a wide range of complex research tasks and high-end enterprise solutions.

multimodal
try online
12.03.2025

Gemma-3-12B

Gemma 3 12B is a high-performance multimodal model with 12 billion parameters, a context window of 128K tokens, and multilingual understanding, designed for a wide range of straightforward tasks. It excels at processing long documents, images, and technical content.

multimodal
12.03.2025

Gemma-3-4B

Gemma 3 4B is a compact model that is also multimodal, featuring a context window of 128K tokens and built-in support for more than 35 languages, including Russian. It's an excellent solution for embedded systems and applications processing text and images with limited computational resources.

multimodal
12.03.2025

Gemma-3-1B

Gemma 3 1B — an ultra-compact model with just 1 billion parameters, yet retaining impressive capabilities. It supports a context window of 32K tokens and is ideal for resource-constrained devices and tasks where response speed is critical.

12.03.2025

QwQ

QwQ is a model with 32.5 billion parameters and a context length of 131K tokens, specifically designed for deep reasoning and logical analysis. Its unique ability to perform transparent and structured thinking sets it apart from competitors, delivering high-quality and well-thought-out responses.

reasoning
try online
06.03.2025

Phi-4-multimodal

Phi-4-multimodal is an efficient solution for multimodal tasks with edge deployment support, combining a compact size (5.6B parameters) with the capabilities of large language models. The model is ideal for developing applications with synchronous processing of speech, images, and text on resource-constrained devices.

multimodal
27.02.2025

Qwen2.5-VL-7B

Qwen2.5-VL-7B is a powerful multimodal model with 7 billion parameters, delivering an optimal balance between high performance and efficiency. Designed for complex document analysis, video stream processing, and agent-based interaction tasks.

multimodal
19.02.2025

Qwen2.5-VL-3B

Qwen2.5-VL-3B - is a compact, 3-billion-parameter multimodal model designed for edge deployment, yet it delivers outstanding capabilities in image/video comprehension and agent-based task execution.

multimodal
19.02.2025

Qwen2.5-7B-1M

Qwen2.5-7B-1M is a compact yet powerful model with 7.6 billion parameters. Thanks to sparse attention technologies, it can process up to one million context tokens at excellent speeds. The model is an ideal solution for organizations requiring high-performance analysis of long documents while optimizing resource usage.

26.01.2025

DeepSeek-R1

DeepSeek-R1 is a unique reasoning model with 671 billion parameters, trained based on reinforcement learning (RL), supporting long chains of thought (CoT), and specializing in multi-step reasoning and logical analysis. It is indispensable for tasks requiring well-founded conclusions and transparent reasoning processes.

reasoning
20.01.2025

DeepSeek-R1-Distill-Qwen-1.5B

DeepSeek-R1-Distill-1.5B — a compact model that, thanks to distillation, possesses strong reasoning capabilities. It is ideal for fast text analysis in mobile and edge applications.

20.01.2025

DeepSeek-R1-Distill-Qwen-32B

DeepSeek-R1-Distill-32B — a model built based on distilling a large MoE reasoning expert-level model, setting new records among open-source dense models. It is suitable for scientific, corporate, and educational platforms with high demands on logic and analysis.

20.01.2025

DeepSeek-V3

DeepSeek-V3 is a powerful MoE model with 671 billion parameters and 16 experts, one of the most popular open-source alternatives capable of competing with commercial analogs. With 128K tokens of context and high generation accuracy, it is ideal for professional tasks - from analyzing complex data to creating high-quality creative content.

26.12.2024

Phi-4

Phi-4 is Microsoft's flagship compact model with 14 billion parameters, designed with a focus on efficiency within a limited context window of 16K tokens. It is optimized for tasks where fast response speed and accuracy are critical in short interactions.

try online
12.12.2024

Llama-3.3-70B

Llama-3.3-70B is a language model supporting 8 languages, featuring a large context window (128k tokens) and high accuracy, making it ideal for assistant and dialogue systems. According to the developers, its performance is on par with Llama 3.1 with 405 billion parameters.

06.12.2024

FLUX.1-Fill-dev

FLUX.1 Fill [dev] is a 12 billion parameter rectified flow transformer capable of filling areas in existing images based on a text description.

21.11.2024

FLUX.1-Kontext-dev

FLUX.1 Kontext [dev] is a 12 billion parameter rectified flow transformer capable of editing images based on text instructions. 

21.11.2024

FLUX.1-Depth-dev

FLUX.1 Depth [dev] is a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. 

try online
21.11.2024

FLUX.1-Canny-dev

FLUX.1 Canny [dev] is 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image.

try online
21.11.2024

shuttle-3-diffusion

Shuttle 3 Diffusion is a text-to-image generation model designed to create detailed and diverse images in just four steps. It offers enhanced image quality, understanding of complex prompts, efficient resource usage, and increased detail.

12.11.2024