Kilo Code

North Mini Code is Cohere's first agentic coding model, a sparse mixture-of-experts with 30B total and 3B active parameters. It has a 256K-token context window with up to 64K tokens of output and interleaved reasoning with tool use. It is open-weight under the Apache 2.0 license.

Dots3-Note Preview is Dots Studio's open-weight mixture-of-experts reasoning model, released as a preview. It has 280B total and 16B active parameters with a 512,000-token context window. It takes text and image input and supports function calling.

LFM 2.5 Embedding 350M is Liquid AI's 354M-parameter multilingual text embedding model covering 11 languages. It returns a 1024-dim CLS vector over 512-token documents. It targets short-context retrieval, FAQ and support search, and cross-lingual search.

Nemotron 3 Embed 1B is NVIDIA's 1.14B-parameter multilingual text embedding model covering 34 languages. It returns 2048-dimension vectors for semantic search, retrieval and RAG. It is built on Ministral-3-3B-Instruct and has a 32,768-token context.

Nemotron-3 Nano Omni 30B-A3B (Reasoning) is NVIDIA's multimodal mixture-of-experts model for video, audio, image and text understanding. It targets enterprise Q&A, summarization, transcription and OCR, and supports reasoning and function calling.

Nemotron 3 Ultra 550B is NVIDIA's 550B-parameter frontier model with 55B active, on a LatentMoE hybrid of Mamba-2, MoE and Attention. It has configurable reasoning through enable_thinking. It suits agentic workflows, long-context analysis and tool use.

Nemotron 3.5 Lightning 30B A3B is NVIDIA's sparse mixture-of-experts chat model, optimized for low-latency agentic workloads. It supports function calling and coding. It allows up to 131,072 output tokens.

Nemotron 3.5 Super VL 120B A12B is NVIDIA's vision-language model for reasoning, coding and tool use. It is a hybrid Mamba-2 and Transformer mixture-of-experts with 120B total and 12B active parameters. It takes text, image and video input.

Beam 1.0 is Reflection's open-weights mixture-of-experts model with 501B total and 23B active parameters. It is built for token-efficient reasoning, agentic tool use, and software engineering. Weights are Apache-2.0.

Glyph Cluster is a reasoning model designed for coding and long-context workloads. It is a stealth preview model from a third-party provider who has chosen to remain anonymous. Input is text only, and function calling is supported. Prompts may be used for training.