Models

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

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

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

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

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

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

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

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

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

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

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

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

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

DeepSeek chat model for instruction following, coding, and analysis

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