Gemini Robotics-ER 1.6

Retired

Embodied-reasoning vision-language model for robotics (spatial understanding, pointing, trajectory planning) - a specialist, not a general chat model. Was preview-only for its whole life. Inputs text/image/video/audio, output text; 131,072 input / 65,536 output tokens (spec table on the model page, which still exists and lists 'Preview: gemini-robotics-er-1.6-preview'). Last published rates: $1.00/M in and $5.00/M out standard, $0.50/$2.50 batch, no separate cached-input rate; the pricing page no longer carries a Gemini Robotics-ER 1.6 section on the 2026-10-20 read, so the price fields are null rather than carried forward. Release date April 14, 2026 read first-party 2026-08-05 from the Release date column of Google's deprecations table (supersedes an earlier note reading the model page's 'spec table latest update December 2025' as not-a-release-date and leaving released null - the table states the real one as data). CONFIRMED RETIRED 2026-10-20 on the only signal this catalog accepts for a Google shutdown: the gemini-robotics-er-1.6-preview row on the deprecations page now carries a literal class="row-gray" on its <tr>, and that page's own legend reads "Already-shutdown models are indicated with gray backgrounds". check-lifecycle-drift.mjs reads that marker and reported Google stating "shut-down" against our "preview". The row was not gray on the 2026-10-19 read (the same script reported drift 0 that day), so the marker appeared between the two reads, 50 days after the published shutdown date of August 31, 2026 (read first-party from the same table on 2026-07-31). Until 2026-10-20 the row was held at preview on purpose: Google states shutdown dates as "the earliest possible dates on which a model might be retired", and a passed date is never sufficient on its own. Its recommended replacement there is gemini-robotics-er-2-preview, added to the catalog 2026-08-02 and now pointed at from this row; Google also offers gemini-robotics-er-2-streaming-preview as an upgrade path for Live API users.

Gemini Robotics-ER 1.6 by Google is tracked live in our LLM catalog, with a 131K (131.072-token) context window. It has been retired (shut down 31 Aug 2026); the recommended migration is Gemini Robotics-ER 2.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Retired on 31 Aug 2026

Provider
Google
Status
Retired
Input price
—
Output price
—
Cached input
—
Blended price
—
Context window
131.072 tokens (131K)
Max output
65.536 tokens
Modality
text, image, video, audio
Open weights
No — API only
Knowledge cutoff
2025-01
Released
14 Apr 2026
API string
gemini-robotics-er-1.6-preview

Source: Google official documentation ↗

FAQ

Gemini Robotics-ER 1.6 — questions & answers

What is the context window of Gemini Robotics-ER 1.6?

Gemini Robotics-ER 1.6 has a 131.072-token context window (131K), with up to 65.536 output tokens per request.

Is Gemini Robotics-ER 1.6 still available?

Gemini Robotics-ER 1.6 has been retired and is no longer available. Its scheduled shutdown date is 31 Aug 2026. The recommended migration is Gemini Robotics-ER 2.

Does Gemini Robotics-ER 1.6 support image or vision input?

Yes — Gemini Robotics-ER 1.6 accepts image input. Listed modalities: text, image, video, audio.

Can I self-host Gemini Robotics-ER 1.6?

No — Gemini Robotics-ER 1.6 is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini Robotics-ER 1.6?

The API model identifier for Gemini Robotics-ER 1.6 is "gemini-robotics-er-1.6-preview" when calling Google's API.

What is Gemini Robotics-ER 1.6's knowledge cutoff?

Gemini Robotics-ER 1.6's training knowledge cutoff is Jan 2025.