Gemini Robotics ER 2 Preview

Preview

google/gemini-robotics-er-2-preview

Google embodied reasoning preview endpoint for robotics, spatial reasoning, multi-step tool orchestration and video progress understanding. It accepts text, images, video and audio, returns text and supports function calling, code execution and structured outputs.

Compare

Context window: 131K
Input: Text · Image · Video · Audio
Output: Text
Released: 2026-07-30

Max output: 66K
Capabilities: Reasoning, Tool call, Structured

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-10-20