Models

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Open GPT reasoning model for self-hosted agents and controllable deployments

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

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

Thinking Kimi model for slower research passes, planning, and hard technical questions

Open GPT reasoning model for self-hosted agents and controllable deployments

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