Models

GPT-5.6 model that balances intelligence and cost

1.05M tokens context

GPT-5.6 model optimized for cost-sensitive workloads

1.05M tokens context

GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.

1.05M tokens context

GPT-5.4 mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.

400K tokens context

cheapest GPT-5.4-class model for simple high-volume tasks

400K tokens context

The best model for coding and agentic tasks with configurable reasoning effort

400K tokens context

The best model for coding and agentic tasks with configurable reasoning effort

400K tokens context

Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort

400K tokens context

Near-frontier intelligence for cost sensitive, low latency, high volume workloads

400K tokens context

Fastest, most cost-efficient version of GPT-5

400K tokens context

Smartest non-reasoning model

1.05M tokens context

Smaller, faster version of GPT-4.1

1.05M tokens context

Fast, affordable small model for focused tasks

128K tokens context

OpenAI's 120-billion parameter open-source general-purpose model for text generation, coding, and reasoning tasks.

128K tokens context

Medium-sized open-weight model for low latency

128K tokens context

256K tokens context

32K tokens context

256K tokens context

256K tokens context

256K tokens context

164K tokens context

128K tokens context

128K tokens context

128K tokens context

128K tokens context