Models

Long coding or research tasks that benefit from adaptive thinking

Anthropic Opus 5 for demanding coding, review, and long-horizon agents

Coding agents, front-end work, and research-heavy tasks

Routing, classification, and guardrail decisions with calibrated probabilities

Low-cost text agents with long prompts and reusable prefixes

Fast coding agents that need image input and a long context

A main coding agent paired with DeepSeek V4 Flash sub-agents

Long-running coding agents that work with images and video

Complex coding and reasoning across long-running tasks

Coordinating agents, planning work, and combining their results

Everyday GPT-6 work where you want to keep costs down

High-volume GPT-5.6 chat, classification, and light agents

GPT-5.6 flagship for CLI-heavy coding and long-horizon problem solving

Harder coding problems and agents that need to work for longer

Affordable image and text tasks with a shorter context

Quick image analysis with a million-token context

Low-cost omnimodal work across text, images, audio, and video

A frontier open-weight agent that reads text, images, audio, and video

Lower-cost coding and visual tasks with a million-token context

Long coding tasks that run for hours and work with text

Long-running coding agents that need a million-token context