Best Input Price
$1.00 / 1M
Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics
Context Window
131,072 tokens
Reasoning
Supported
Tool Calling
Supported
Released
2026-04-14
Inference Providers (1)
| Provider | Model ID | Context | Input / 1M | Output / 1M | Action |
|---|---|---|---|---|---|
| OrcaRouter | google/gemini-robotics-er-1.6-preview | 131,072 | $1.00 | $5.00 | Docs ↗ |