AI Model Catalogue

Open-source NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source tiny-random-LlamaForCausalLM model from hmellor — available for download and self-hosting on Hugging Face.

Open-source Llama-2-7b-hf model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source GLM-5-FP8 model from zai-org — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Embedding-8B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Thinking-2507 model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Embedding-4B model from qwen — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-R1-Distill-Llama-8B model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source pythia-160m model from eleutherai — available for download and self-hosting on Hugging Face.

Open-source distilgpt2 model from distilbert — available for download and self-hosting on Hugging Face.

Open-source gpt2-large model from openai-community — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3-8B model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source gpt-oss-120b model from openai — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-R1 model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source gpt-oss-20b model from openai — available for download and self-hosting on Hugging Face.

Open-source opt-125m model from facebook — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Instruct-2507 model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B model from qwen — available for download and self-hosting on Hugging Face.

Open-source gpt2 model from openai-community — available for download and self-hosting on Hugging Face.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...