Models

Claude model for creative writing, analysis, and controlled agent workflows

Reasoning-first Gemini preview for agentic coding and complex problem solving

Default frontier GPT for coding, computer use, research, and knowledge work

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

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

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

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

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

Low-latency Gemini model for high-volume multimodal and agent workloads

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

Reliable GPT generation for broad coding, writing, and tool-assisted product work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

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

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

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

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

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

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