Pricing · Google
Gemini Robotics ER 2 Preview
Google's gemini-robotics-er-2-preview, 131K tokens of context. Every number on this page was read off Google's own pricing
page — never estimated, never recalled from memory.
How Google describes it
“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.”
Pricing
| Input | $1.00 | per 1M tokens |
|---|---|---|
| Output | $5.00 | per 1M tokens |
| Cached input | $0.10 | per 1M tokens · 0.1× the input price |
At the calculator's starting volume, 1M input tokens and 200K output tokens with no cache hits, Gemini Robotics ER 2 Preview costs $2.00: $1.00 for input and $1.00 for output, at the promotional prices above. Same formula as the calculator; change the volume there.
Where this price sits
$1.00 per 1M input tokens is the 22nd cheapest input price of the 67 current models with a verified price on this site, and the 7th of Google's 11. Output costs 5.0× the input price.
Other current models in the Gemini Robotics family:
- Gemini Robotics ER 2 Streaming Preview 131K tokens $1.00 in · $5.00 out · promo
Mentioned in
One post on this site cites Gemini Robotics ER 2 Preview. The sentence is the post's own, taken from where it links here.
-
Prompt Caching Is Not 10% Everywhere: What a Cache Hit Costs Across Eight Providers · September 16, 2026 · 2 mentions
Google, all ten Gemini models with a cache price, from Gemini 2.5 Flash-Lite at $0.01 on $0.10 to Gemini 2.5 Pro at $0.125 on $1.25, September 14, and Gemini Robotics ER 2 Preview at $0.10 on $1.00, September 16.
Recorded price changes
Every change this site has recorded for Gemini Robotics ER 2 Preview, with the date it took or takes effect and why. Corrections of our own reading are listed too, and say so.
-
September 16, 2026 · added to this dataset, our omission
Omission on our side, not a price change by any provider. On September 16, 2026, while reading OpenAI's pricing page by hand for a check on batch and flex prices, GPT-6 Astra turned up in the Standard table with no row in this dataset. A hand sweep of the first-party pricing pages of OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Alibaba and Cohere against the dataset then found eight models charged per token with text output and a published price that had no row: GPT-6 Astra and GPT-Rosalind (OpenAI), Claude Haiku 3.5 (Anthropic, retired on the first-party API but still priced), Gemini 2.5 Computer Use Preview, Gemini Robotics ER 2 Preview and its Streaming variant, and Gemini Omni Flash Preview, a separate endpoint id from the generally available Omni Flash row at the same prices (Google), and GLM 5.3 (served by Mistral). Astra had been in OpenAI's Standard table at least since September 10, 2026, when the weekly detector first received that page's text, and this site's OpenRouter explainer already named it from the September 15 snapshot. The weekly detector could not have caught any of these: it compares the rows that exist against the page and has no step for models the page lists and the dataset does not. Each new row carries the page quote it was read from. Audio, image, video, embedding and per-minute models found in the same sweep were left out on purpose: the table covers models charged per token with text output.
Every price change recorded on this site →
Specifications
| API model id | gemini-robotics-er-2-preview | |
|---|---|---|
| Provider | ||
| Family | Gemini Robotics | |
| Context window | 131K tokens | |
| Max output | 66K tokens | |
| Status | Current | |
It returns up to 66K tokens per response, against a context window of 131K tokens.
Questions about Gemini Robotics ER 2 Preview pricing
- How much does Gemini Robotics ER 2 Preview cost per million tokens?
- $1.00 per 1M input tokens and $5.00 per 1M output tokens, read on Google's official pricing page on October 1, 2026.
- What does a cached input token cost on Gemini Robotics ER 2 Preview?
- $0.10 per 1M cached input tokens, 10% of the $1.00 input price.
- Is Gemini Robotics ER 2 Preview's price a promotion?
- Yes. $1.00 input and $5.00 output are promotional prices until December 31, 2026; the list price Google publishes for after that is $2.00 input and $10.00 output per 1M tokens.
Added 2026-09-16 after a hand sweep of Google's pricing page found it missing from this dataset (our omission). Page block 'Gemini Robotics ER 2 Preview gemini-robotics-er-2-preview … a vision-language model endpoint that enables robots to understand their environments precisely'. Paid Tier: 'Input price … $1.00 (text / image / video / audio) through December 31, 2026. $2.00 (text / image / video / audio) starting January 1, 2027. Output price (including thinking tokens) … $5.00 through December 31, 2026. $10.00 starting January 1, 2027. Context caching price … $0.10 through December 31, 2026. $0.20 starting January 1, 2027.' The page also prints a cache storage price ($0.50 per million tokens per hour through December 31, 2026, $1.00 after), not stored as a field. No context window on the page. Google gives an input token limit, not a context window; contextWindow here is that input limit. Read on Google's model page (ai.google.dev/gemini-api/docs/models/gemini-robotics-er-2-preview) on 2026-09-30: 'Input token limit 131,072', 'Output token limit 65,536'.
Verified October 1, 2026 against Google's official pricing page. Confidence: confirmed. How the data is checked.
Other Google models with a verified price
- Gemini 2.5 Flash-Lite Gemini Flash-Lite $0.10 in · $0.40 out
- Gemini 3.5 Flash-Lite Gemini Flash-Lite $0.30 in · $2.50 out
- Gemini 2.5 Flash Gemini Flash $0.30 in · $2.50 out
- Gemini 3.8 Flash Gemini Flash $0.75 in · $3.75 out · promo
- Gemini 3.7 Flash Gemini Flash $0.75 in · $3.75 out · promo
- Gemini 3.6 Flash Gemini Flash $0.75 in · $3.75 out · promo
- Gemini Robotics ER 2 Streaming Preview Gemini Robotics $1.00 in · $5.00 out · promo
- Gemini 2.5 Pro Gemini Pro $1.25 in · $10.00 out
- Gemini 3.5 Flash Gemini Flash $1.50 in · $9.00 out
- Gemini 3.1 Pro Preview Gemini Pro $2.00 in · $12.00 out
Cheaper or equally priced alternatives
Current models with an input price at or below $1.00 per 1M tokens.
- Claude Haiku 4.5 Anthropic $1.00 in · $5.00 out
- Gemini Robotics ER 2 Streaming Preview Google $1.00 in · $5.00 out · promo
- Grok Build 0.1 xAI $1.00 in · $2.00 out
- Gemini 3.8 Flash Google $0.75 in · $3.75 out · promo
Compare every model in one table →
Work out what this costs at your volume →