Models
Browse and use state-of-the-art AI models for inference. Select a model to get started with your AI tasks.
Featured Models
LLaMA 3.1
text-generationcodingreasoning
Meta's latest iteration in the LLaMA series, offering models with up to 405 billion parameters, primarily focusing on text generation and coding support.
DeepSeek-R1
reasoningefficiencyperformance
Developed by DeepSeek, emphasizing reasoning capabilities, trained at a cost of approximately $5.6 million, and recognized for its efficiency and performance.
Mistral 7B
text-generationefficiencyscalability
A 7.3 billion parameter language model using the transformers architecture, known for its efficiency and scalability.
Flux
text-to-imagediffusionmultimodal
Developed by Black Forest Labs, Flux is a text-to-image model based on a hybrid architecture combining multimodal and parallel diffusion transformer blocks.
All Models
Available Models
Sort by:
| Model | Category | Parameters | Release Date | License | Action |
|---|---|---|---|---|---|
Bark A transformer-based text-to-audio model from Suno that can generate realistic speech, music, and sound effects. | audio | 2.9B | April 15, 2023 | MIT License | Use |
CogVLM A vision-language model developed by THUDM that excels at complex visual reasoning tasks and detailed image understanding. | multimodal | 17B | October 10, 2023 | Apache 2.0 | Use |
DBRX A mixture-of-experts transformer model that outperforms other prominent open-source models in language understanding, programming ability, and mathematics. | text | 132B | March 27, 2024 | Databricks Open License | Use |
DeepSeek-R1 Developed by DeepSeek, emphasizing reasoning capabilities, trained at a cost of approximately $5.6 million, and recognized for its efficiency and performance. | text | 671B | January 20, 2025 | MIT License | Use |
Falcon Developed by the Advanced Technology Research Council in Abu Dhabi, Falcon models surpassed those from Meta and Google at the time of release. | text | 40B | June 15, 2023 | Apache 2.0 | Use |
Flux Developed by Black Forest Labs, Flux is a text-to-image model based on a hybrid architecture combining multimodal and parallel diffusion transformer blocks. | image | 12B | August 15, 2024 | Apache License (Schnell), Non-commercial license (Dev), Proprietary (Pro) | Use |
Fuyu-8B Adept's multimodal model designed for document understanding, with strong capabilities for processing text within images and diagrams. | multimodal | 8B | October 20, 2023 | Adept Model License | Use |
Gemma 1.1 Vision Google's open-source multimodal model that combines vision and language capabilities, designed for image understanding and visual reasoning tasks. | multimodal | 9B | June 10, 2024 | Gemma License (Open) | Use |
GPT-J A 6 billion parameter language model developed by EleutherAI, serving as a free alternative to OpenAI's GPT-3. | text | 6B | March 15, 2021 | Apache 2.0 | Use |
IDEFICS 2 Hugging Face's open-source multimodal model that can understand and generate text based on images, with strong performance on visual reasoning tasks. | multimodal | 8-80B | May 15, 2024 | Apache 2.0 | Use |
Showing 1-10 of 24 models