Gemini 3.5 Flash: price, context window and ranking
As of 22 October 2026, Gemini 3.5 Flash from Google costs $1.50 per million input tokens and $9.00 per million output tokens on OpenRouter, with a context window of 1.05M tokens. On the LMArena text leaderboard it ranks 18 with a score of 1,482.0.
- Input price
- $1.50
- Output price
- $9.00
- Context window
- 1.05M
- LMArena score
- 1,482.0
- Providers
- 7
per 1M tokens
per 1M tokens
tokens
rank 18
uptime 85.6%
Specifications
| Field | Value |
|---|---|
| Provider | |
| Input price per 1M tokens | $1.50 |
| Output price per 1M tokens | $9.00 |
| Blended price per 1M tokens (3:1) | $3.375 |
| Context window | 1,048,576 |
| Providers serving it | 7 |
| Average uptime, past day | 85.6% |
| LMArena | 1,482.0 (rank 18) |
| Arena score per dollar | 439.1 |
| Added to OpenRouter | 2026-05-19 |
| Modality | text+image+file+audio+video->text |
| OpenRouter model ID | google/gemini-3.5-flash |
Price history
- Input
- Output
| Date | Input | Output |
|---|---|---|
| 2026-10-16 | $1.50 | $9.00 |
| 2026-10-17 | $1.50 | $9.00 |
| 2026-10-18 | $1.50 | $9.00 |
| 2026-10-19 | $1.50 | $9.00 |
| 2026-10-20 | $1.50 | $9.00 |
| 2026-10-21 | $1.50 | $9.00 |
| 2026-10-22 | $1.50 | $9.00 |
Frequently asked questions
How much does Gemini 3.5 Flash cost per million tokens?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens on OpenRouter, as of 22 October 2026. At a mix of three parts input to one part output the blended price is $3.375 per million tokens.
What is the context window of Gemini 3.5 Flash?
Gemini 3.5 Flash has a context window of 1.05M tokens (1,048,576 exactly).
How does Gemini 3.5 Flash rank on LMArena?
Gemini 3.5 Flash is ranked 18 on the LMArena text leaderboard with a score of 1,482.0 from 48,479 votes. The listing used is "Gemini 3.5 Flash (High)".
When was Gemini 3.5 Flash released?
OpenRouter lists Gemini 3.5 Flash as added on 19 May 2026.
Who provides Gemini 3.5 Flash?
Gemini 3.5 Flash is served by 7 providers on OpenRouter, with average uptime of 85.6% over the past day.
Methodology and sources
The catalogue, prices, context lengths and provider counts come from OpenRouter's public Models API. They are fetched every day at 06:00 Istanbul time and stored as a daily snapshot. Weekly changes are calculated by Oesnada by comparing those snapshots; there is no data before 16 October 2026.
Usage shares are calculated from the daily token totals of OpenRouter's Data API: a model's tokens over the past 7 days divided by all tokens in the same period, including the aggregated long tail outside the top 50. Token counts come from each provider's own tokenizer and are not directly comparable across providers. The data is published by OpenRouter under CC BY 4.0. Variants such as ":free" are counted separately, so shares here can differ from OpenRouter's own ranking page.
Quality rankings come from LMArena's text (overall) leaderboard. A model is matched only when its name matches exactly; if a model has several listings, the highest-scoring one is used. "Frontier" means a model in the LMArena top 15.
"Best value" divides the LMArena score by the blended price (three parts input to one part output). Arena scores are not a linear scale, so the ratio is a rough guide. This page is produced automatically.
- OpenRouter Models API
- OpenRouter Rankings (Data API) (CC BY 4.0)
- LMArena leaderboard dataset (CC BY 4.0)
Related Oesnada stories: Google
- Epic Says Fortnite Returns to Australian App Store Tomorrow After Court Ruling
The orders cover only the Australian App Store and users with an Australian Apple Account, and the judge rejected Epic's request for worldwide relief, citing the regulatory choices of other jurisdictions such as the EU and Japan.
Importance 93/100 - LiteLLM Supply Chain Attack Steals Passwords and Secrets
LiteLLM provides a common interface to LLM providers such as OpenAI, Anthropic, and Google Gemini, and gets about 23 million weekly downloads.
Importance 90/100 - OpenAI and Google's Wiz Find Ancient PHP Vulnerabilities, Raising Internet
PHP runs about 70% of websites whose server-side language is known, and Wiz says every version from the past decade is affected by at least one flaw, going back to PHP 5.4.
Importance 95/100 - $15 billion ad-powered AI startup may already be used by your doctor
The tool's reach matters because it is influencing clinical decisions in a field where few software products have caught on this quickly.
Importance 90/100 - OpenAI Models Coming to Google Cloud
For customers, the change means they can use OpenAI's models in the same environment where their developers and data scientists already build AI workloads.
Importance 90/100
All AI models
Download the data
Cite this page
Oesnada, "Gemini 3.5 Flash: price, context window and ranking", https://oesnada.com/ai-models/google-gemini-3-5-flash, accessed 22 October 2026.