GoogleFrontierfree tierpreview

Gemini Robotics ER 2 Preview

API id: gemini-robotics-er-2-preview

Gemini Robotics ER 2, short for Gemini Robotics Embodied Reasoning 2, is a vision-language model endpoint that enables robots to understand their environments precisely, supporting agentic orchestration of robots, video progress understanding, multi-robot collaboration, and advanced spatial reasoning.

Input / output price
$1 / $5
per 1M tokens · standard

Where it's used

Rank among current models on each use case's benchmark

All prices

Read from Google's pricing page

TierInputCached inputOutput
Standard$1$0.10$5
Batch$0.50$0.05$2.50
  • input: $1.00 (text / image / video / audio) through December 31, 2026. · $2.00 (text / image / video / audio) starting January 1, 2027.
  • cachedInput: $0.10 through December 31, 2026. · $0.20 starting January 1, 2027. · $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. · $1.00 / 1,000,000 tokens per hour (storage price) starting January 1, 2027.
  • output: $5.00 through December 31, 2026. · $10.00 starting January 1, 2027.

Related models