Guide

DeepSeek V4.1 Flash model for reasoning and agentic coding

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

Flagship GLM model for long-horizon coding, agents, and complex project delivery

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

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

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

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

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

MiniMax multimodal coding model for long-context reasoning and agent tasks

Flagship DeepSeek model for coding, reasoning, and agentic work

Fast DeepSeek model for efficient chat, coding help, and agent loops

Kimi multimodal agent model for visual understanding, coding, and planning

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

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

MiniMax model for chat, coding, office work, and agentic tasks

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

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

MiniMax model for chat, coding, office work, and agentic tasks

Kimi multimodal agent model for visual understanding, coding, and planning

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

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Open-weight GPT model for self-hosted reasoning and instruction-following workloads