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

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

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

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

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

Flagship Qwen model for complex reasoning, coding, and agentic workflows

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

Flagship DeepSeek model for coding, reasoning, and agentic work

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

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

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

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

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

Open-weight instruction model for adaptable chat and self-hosted production workloads

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

Legacy model retained for compatibility with older integrations

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

Legacy model retained for compatibility with older integrations

Open-weight instruction model for adaptable chat and self-hosted production workloads

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Legacy model retained for compatibility with older integrations

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

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

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

Legacy model retained for compatibility with older integrations

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

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Compact Llama instruction model for fast chat and local deployment

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Compact Llama instruction model for fast chat and local deployment