All Models

Latest flagship with 1M context window and strong coding/instruction following

Affordable intelligence with 1M context — best cost/performance in the 4.1 family

Multimodal model with strong vision, audio, and text capabilities

Ultra-affordable model for high-volume tasks with good quality

Advanced reasoning model at significantly reduced price (80% cut from launch)

Fast, efficient reasoning model optimized for STEM and coding tasks

Most capable Claude model — step-change improvement in agentic coding

Optimal balance of intelligence, cost, and speed with 1M context

Fastest and most cost-efficient Claude with near-frontier intelligence

Previous flagship — strong reasoning and extended thinking support

Most capable Gemini model with deep reasoning and multimodal support

Best-in-class speed and efficiency for diverse tasks

Most cost-efficient Gemini model for high-volume, latency-sensitive workloads

Frontier-level MoE model (675B total / 41B active params) at competitive price

Mistral's reasoning model — strong for complex analytical and math tasks

State-of-the-art performance at 8x lower cost than previous generation

Efficient small model for simple, high-volume tasks

Code-specialized model with 256k context — optimized for fill-in-the-middle