A fast and cost-effective model with native tool use, code execution, and web search grounding. Supports a 1M token context window with multimodal inputs including text, images, audio, and video. Experimental thinking support enables configurable reasoning. Ideal for high-volume tasks that need broad capability at minimal cost.
Try NowNeed cheapest possible model with tool use
Simple multimodal task at low cost
High-volume processing where 2.5 is unnecessary
1,048,576 tokens
8,192 tokens
$0.15 per 1M tokens
$0.60 per 1M tokens
$0.0375 per 1M tokens
$35 per 1K calls
$0 per 1K calls