Self-Hosted AI

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.

123B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.

Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.

DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.

The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.

Granite 4 features improved instruction following (IF) and tool-calling capabilities, making them more effective in enterprise applications.

gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

Alibaba's performant long context models for agentic and coding tasks.

A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

The 7B model released by Mistral AI, updated to version 0.3.

Devstral: the best open source model for coding agents

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

An update to Mistral Small that improves on function calling, instruction following, and less repetition errors.

Magistral is a small, efficient reasoning model with 24B parameters.

Meta's latest collection of multimodal models.

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.

Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.

Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.

Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.