Models

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

Open coding-reasoning model for repository tasks and self-improving agents

Open coding-reasoning model for repository tasks and self-improving agents

Large coding-reasoning model for agentic software tasks and RL search

Large coding-reasoning model for agentic software tasks and RL search

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

MiniMax multimodal model for long-context coding, perception, and agent planning

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

Cohere's stronger command model for multilingual agents and enterprise workflows

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Open Nemotron omni model combining reasoning with text, vision, and audio

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

Qwen vision-language model for visual reasoning, documents, and agent tasks

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Open Gemma instruction model for efficient chat and self-hosted deployments

Open Gemma instruction model for efficient chat and self-hosted deployments

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Reranking model for improving retrieval quality in search and recommendation systems

Efficient Mistral model for fast chat, extraction, and production assistants

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen instruction model for multilingual chat, reasoning, and tool use

Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks

Large open Qwen multimodal MoE for visual agents and long technical tasks

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Compact multimodal coding model for repository exploration, file editing, and software agents

GLM vision model for visual reasoning, documents, and multimodal agents

Lightweight GLM vision model for visual reasoning, documents, and multimodal agents

Compact open vision-language model for edge deployment, instruction following, and tool use

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Open vision-language model for efficient local deployment, instruction following, and tool use

Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use

Compact open vision-language model for edge deployment, instruction following, and tool use