Models

DeepSeek V4.1 Flash model for reasoning and agentic coding

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

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Agentic coding model from Poolside in the XS size class for local deployment

Open flagship GLM for long-horizon coding agents and million-token context work

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Cohere coding model for practical software engineering and agentic edits

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

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

Newer StepFun flash model for faster agents, coding, and multimodal prompts

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

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

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Open MoE flagship with million-token context for coding and long agent runs

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

Open MiMo model for multimodal coding agents and long-context automation

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

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Tencent Hy reasoning model for coding, instruction following, and agent tasks

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

Strong GLM coding model for agentic engineering, terminals, and repository generation

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

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

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Open MiniMax flagship for coding agents, office automation, and complex environments

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

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

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

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

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

Prior MiniMax coding model for agent workflows, office edits, and automation

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

StepFun flash lane for quick multimodal reasoning and coding assistance

Budget GLM lane for fast coding help, routing, and everyday automation

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Earlier MiniMax agent model for practical coding and productivity tasks

Mature GLM model for dependable coding, reasoning, and structured agent tasks

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use