Best Input Price
$0.88 / 1M
Efficient model for low-latency assistance, extraction, and routine automation
Context Window
128,000 tokens
Reasoning
Supported
Tool Calling
Supported
Released
2026-07-08
Best Input Price
$0.88 / 1M
Efficient model for low-latency assistance, extraction, and routine automation
128,000 tokens
Supported
Supported
2026-07-08