One Interface for all AI models

Multimodal flagship model with vision, audio, and text capabilities. Faster and cheaper than GPT-4 Turbo.

Affordable, intelligent small model for fast, lightweight tasks. Supports vision and function calling.

Reasoning model optimized for STEM and coding. Delivers high capability at a fraction of o1 pricing.

Most intelligent Claude model with extended thinking mode. Best for complex reasoning, coding, and agentic tasks.

Fast, affordable model with strong performance. Great for high-volume, latency-sensitive workloads.

Fast, capable multimodal model with native tool use, spatial understanding, and real-time audio/video.

Reasoning variant of Gemini 2.0 Flash with visible thought process. Excels at complex multi-step problems.

Frontier model from xAI with real-time knowledge access. Strong at math, reasoning, and coding.

Open-weight reasoning model rivalling o1 at a fraction of the cost. Excellent for math and coding.

Reasoning model from Alibaba with strong math and coding performance. Open-weight and cost-effective.

Large Mixture-of-Experts model with 456B parameters and 45.9B active. Massive 1M token context window.