Models

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

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

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

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

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

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

Faster GLM-5 lane for coding agents that need lower latency

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

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

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

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

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

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

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

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

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

Smaller Qwen coder for efficient local agents and repo-level fixes