Models

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Strongest Claude Opus model for coding, agents, and professional work

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

OpenAI model for complex coding and agentic workflows

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

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

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

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

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

OpenAI's most efficient model for focused, high-volume tasks

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

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

Thinking Kimi model for slower research passes, planning, and hard technical questions

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

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

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Multimodal reasoning model for visual analysis, planning, and tool use

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Open multimodal Gemma instruction model for efficient text generation and image understanding

Open multimodal Gemma instruction model for multilingual text generation and image understanding