Models

000

Dots3-Note Preview is an open-weight mixture-of-experts model developed by Dots Studio, featuring 16B active parameters out of 280B total. As the lightest model in the Dots 3 family, it is designed for efficient performance while supporting an expansive context length of 512,000 tokens. This preview version provides an accessible way to experience the capabilities of the Dots 3 architecture.

Mercury 2.5 is Inception's diffusion language model (dLLM), designed for text generation and reasoning tasks. Instead of sequential generation, it produces and refines multiple tokens in parallel to achieve rapid reasoning, supported by an expansive 260,000-token context window.

gpt-5.6-sol-pro is OpenAI's multimodal model, designed for complex reasoning and generation tasks. It supports text and image inputs alongside an extensive 1,050,000-token context window. Compared with GPT-5.6 Sol, it is served with reasoning.mode set to pro for higher-quality responses on complex tasks.

qwen3.8-27b is Qwen's open-weight dense vision-language model, designed for coding, professional workflows, research, multimodal interaction, and long-running agent tasks. It supports text and image inputs with an extensive 1,000,000-token context length and flexible thinking capabilities.

LFM-2.5-2.6B is a compact reasoning model developed by Liquid, featuring a generous 128,000 token context length. It is highly suited for agent workflows, data extraction, retrieval-augmented generation (RAG), and long-context processing. However, the developer advises against using this model for agentic coding tasks.

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring 3 billion active parameters out of 30 billion total. It supports an extensive context window of up to 1,000,000 tokens. This model is designed to deliver efficient performance for high-throughput agentic workloads and specialized tasks. Compared with Nemotron 3 Super and Ultra, Lightning is smaller and opti…

Developed by Cohere, north-mini-code-free is the debut model of the North family and Cohere's first agentic coding model. This sparse mixture-of-experts model features 30B total parameters and 3B active parameters, designed and optimized for high performance. With an expansive context length of 256,000 tokens, it is well-suited for handling complex developer workflows and large codebases.

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model featuring an extensive 1,000,000-token context length. Built on a hybrid Transformer-Mamba mixture-of-experts (MoE) architecture, it operates with 55B active parameters out of a total of 550B parameters. This advanced structure is designed to support sophisticated reasoning and complex task orchestration.

Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. Supporting an expansive context length of 128,000 tokens, this model moderates both user inputs and generated responses for LLMs and VLMs. It provides robust safety filtering to ensure aligned and secure interactions across multiple modalities.

Developed by Nvidia, NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. Supporting a massive context length of 256,000 tokens, it accepts and processes inputs across text, images, and video. This model provides powerful multimodal comprehension tailored for complex enterprise workflows.

NVIDIA Nemotron 3 Nano 30B A3B is a highly efficient small language Mixture of Experts (MoE) model developed by Nvidia. Designed to help developers build specialized agentic AI systems, it delivers exceptional compute efficiency and accuracy. Additionally, it features an impressive context length of 256,000 tokens to support extensive data processing.

Kimi K2 Thinking is Moonshot AI's most advanced open-source inference model to date, extending the K2 series into intelligent agent and long-context inference domains. The model is built on the trillion-parameter mixture of experts (MoE) architecture introduced by Kimi K2, activating 32 billion parameters per forward pass and supporting a context window of 256,000 tokens.

Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It features a powerful 128,000-token context length to handle extensive visual and textual inputs. The model utilizes a hybrid Transformer-Mamba architecture, successfully combining transformer-level accuracy with Mamba's structu…

coding-minimax-m2 is a free and open version offered by AIHubMix specifically for MiniMax users. To maintain stable service operations, the following usage limits apply: a maximum of 10 requests per minute, 1,000 total requests per day, and a daily quota of 5 million tokens.204800

NVIDIA-Nemotron-Nano-9B-v2-free is a large language model trained from scratch by NVIDIA. Designed as a unified model, it efficiently handles both reasoning and non-reasoning tasks to respond to a wide range of user queries. With a generous context length of 128,000 tokens, it is highly capable of processing long and complex documents.

Mistral Large 3 is a MoE model with 67.5B total parameters and 41B active parameters, supporting a 256K-token context window. Trained from scratch on 3,000 NVIDIA H200 GPUs, it is one of the strongest permissively licensed open-weight models available. Designed for advanced reasoning and long-context understanding, Mistral Large 3 delivers performance on par with the best instruction-tuned open…