google/gemini-robotics-er-1.6-preview

google/gemini-robotics-er-1.6-preview
VisionAudioToolsJSONReasoning
by google

Google's multimodal preview model for robotics, supporting text, image, video, and audio inputs with up to 65,536 output tokens.

Max output65K
Inputtext + image + video + audio
p50 TTFT1.47 s
INPUT$1.00/ 1M tokens
OUTPUT$5.00/ 1M tokens
p50 TTFT1.47 s7d
p95 TTFT2.45 s7d
TRAFFIC1.8Mtokens / 7d

google/gemini-robotics-er-1.6-preview is a preview model from Google's Gemini family optimized for robotics and embodied reasoning. It is a multimodal model that can process text, images, video, and…

What is google/gemini-robotics-er-1.6-preview?

Who should use this model?

What are the key input and output capabilities?

How is this model accessed via OrcaRouter?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Gemini SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="google/gemini-robotics-er-1.6-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • max_tokens
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p
  • include_reasoning
  • reasoning

Pricing

Input / 1M tokens$1.00
Output / 1M tokens$5.00
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $22.00

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.002520

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.47 s
Output speed
259 tok/s
p95 TTFT
2.45 s
Error rate
0%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News0 mentions · 7d

How it compares

google/gemini-robotics-er-1.6-previewGemini 3.1 Pro PreviewGemini 3.1 Pro Preview Custom ToolsGemini 3 Flash Preview
Input $/M$1.00$2.00$4.00$0.50
Output $/M$5.00$12.00$18.00$3.00
Context1.0M1.0M1.0M
Quality5/1010/1010/109/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does it cost to use google/gemini-robotics-er-1.6-preview on OrcaRouter?
Pricing is $1.00 per 1 million input tokens and $5.00 per 1 million output tokens, billed at Google's provider rate with zero markup. There are no extra fees from OrcaRouter.
What is the maximum output token limit?
The model supports up to 65,536 output tokens per request. Input token limits are not specified but are expected to be large given the multimodal input options.
What are the input modalities supported?
The model accepts text, image, video, and audio inputs. You can combine these modalities in a single request. Output is text only.
What are the main strengths of this model?
Its main strengths are multimodal input (text, image, video, audio) and a very large output context of 65,536 tokens, making it well-suited for robotics tasks that require long plans or code.
How does it compare to Gemini 1.5 Pro?
Gemini 1.5 Pro is a general-purpose multimodal model with a smaller output context (typically 8,192). The robotics-er preview offers a much larger output and is specialized for embodied reasoning. Pricing is similar, but the preview model may have less general knowledge.
Does OrcaRouter cache prompts to reduce cost?
No, OrcaRouter does not apply caching. You can implement client-side caching of responses for repeated identical inputs to save costs.
How do I call the model via the API?
Use OrcaRouter's OpenAI-compatible API at https://api.orcarouter.ai/v1 with model id 'google/gemini-robotics-er-1.6-preview'. Send a POST request to the /chat/completions endpoint with your API key and standard parameters.
Is data handled differently when using this model through OrcaRouter?
OrcaRouter acts as a proxy, passing requests to Google's API. Data is processed according to Google's privacy policy. OrcaRouter does not store or log your prompts by default; review OrcaRouter's data processing terms for details.
What if I don't need multimodal inputs or large output? Should I use a cheaper model?
Yes, if your use case is text-only or requires short outputs, consider using a less expensive model like Gemini 1.5 Flash or a cheaper text-only model available through OrcaRouter. The robotics-er model is optimized for high-cost, multimodal, long-output scenarios.
Are there any benchmark results for this model?
No, Google has not published benchmark scores for this preview model. Users should evaluate its performance on their own datasets. OrcaRouter does not provide additional benchmarks.

Embed this badge

google/gemini-robotics-er-1.6-preview$1.00/M in1466ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/google/gemini-robotics-er-1.6-preview" target="_blank"> <img src="https://www.orcarouter.ai/embed/google/gemini-robotics-er-1.6-preview.svg" alt="google/gemini-robotics-er-1.6-preview on OrcaRouter" /> </a>
Markdown [![google/gemini-robotics-er-1.6-preview](https://www.orcarouter.ai/embed/google/gemini-robotics-er-1.6-preview.svg)](https://www.orcarouter.ai/models/google/gemini-robotics-er-1.6-preview)

Model card as data

GET /api/public/models/google/gemini-robotics-er-1.6-previewOpen
Machine-readable:/llms.txt/llms-full.txt