Models

DeepSeek V4.1 Flash model for reasoning and agentic coding

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

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

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

Balanced GPT-5.6 model for capable, cost-efficient everyday work

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Cost-efficient GPT-5.6 model for fast, high-volume workloads

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

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

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

Everyday Claude agent model for coding, planning, browsing, and general work

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Stronger Opus tier for advanced software work and high-stakes reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

Agent-ready GPT for coding and computer-use workflows at a lower cost

Claude workhorse for coding agents, careful analysis, and production cost control

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

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

Fast Gemini model balancing multimodal reasoning, tool use, and cost