Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

google/gemini-3.6-flash

Organization: Google
Family: gemini-flash
Providers: 26
Context: 1,048,576
Output limit: 65,536
Knowledge: 2026-03
Release: 2026-07-21
Updated: 2026-07-21
Weights: Closed
Input: text, image, video, audio, pdf
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

36 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Abacus	gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
AIHubMix	gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Cortecs	gemini-3.6-flash	1,048,576	65,535	$0.75 / $3.75	Yes	Yes	Yes	View
CrossModel	gemini/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
DevPass (LLM Gateway)	gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	google/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.6-flash@eu	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.6-flash@us	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
GitHub Copilot	gemini-3.6-flash	1,000,000	64,000	$0.75 / $3.75	Yes	Yes	Yes	View
Google	gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Impossibl	google/gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Kenari	gemini-3-6-flash	1,048,576	65,536	$0.00 / $0.00	Yes	Yes	Yes	View
Kilo Gateway	google/gemini-3.6-flash	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
LLM Gateway	google-ai-studio/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
LLM Gateway	google-vertex/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Merge Gateway	google/gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
NanoGPT	google/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Neon	gemini-3-6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Ofox	google/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
OpenCode Zen	gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$0.825 / $4.125	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.6-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
OrcaRouter	google/gemini-3.6-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Pioneer	gemini-3.6-flash	1,000,000	64,000	$1.50 / $7.50	Yes	Yes	Yes	View
Requesty	gemini-3.6-flash	1,048,576	65,535	$1.50 / $7.00	Yes	Yes	Yes	View
Tempr Gateway	google/gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Venice AI	gemini-3-6-flash	1,000,000	65,536	$0.9375 / $4.6875	Yes	Yes	Yes	View
Vercel AI Gateway	google/gemini-3.6-flash	1,000,000	64,000	$0.75 / $3.75	Yes	Yes	Yes	View
Vertex	gemini-3.6-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers36Across 26 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 7 lowest-priced configurations

InputOutput

Googlegoogle-vertex/global/flex

$0.375$1.875

Google AI Studiogoogle-ai-studio/flex

$0.375$1.875

Googlegoogle-vertex/global

$0.75$3.75

Google AI Studiogoogle-ai-studio

$0.75$3.75

Googlegoogle-vertex/us

$0.825$4.125

Googlegoogle-vertex/global/priority

$1.35$6.75

Google AI Studiogoogle-ai-studio/priority

$1.35$6.75

google/gemini-3.6-flashObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.75
Output: $3.75
Cache read: $0.075
Cache write: $0.041667

Additional fees and pricing conditions

audio: $0.00000075 / audio token
image: $0.00000075 / image
web search: $0.014 / search
input audio cache: $0.000000075 / audio token
internal reasoning: $0.00000375 / reasoning token

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Googlegoogle-vertex/us	$0.825	$4.125	$0.0825	$0.041667
Googlegoogle-vertex/global/flex	$0.375	$1.875	$0.0375	$0.020833
Googlegoogle-vertex/global/priority	$1.35	$6.75	$0.135	$0.075
Googlegoogle-vertex/global	$0.75	$3.75	$0.075	$0.041667
Google AI Studiogoogle-ai-studio/priority	$1.35	$6.75	$0.135	$0.075
Google AI Studiogoogle-ai-studio/flex	$0.375	$1.875	$0.0375	$0.020833
Google AI Studiogoogle-ai-studio	$0.75	$3.75	$0.075	$0.041667

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Googlegoogle-vertex/us

1,074–2,318 ms

Googlegoogle-vertex/global/flex

10,509–53,720.46 ms

Googlegoogle-vertex/global/priority

3,051–7,287.88 ms

Googlegoogle-vertex/global

1,310–8,317.62 ms

Google AI Studiogoogle-ai-studio/priority

3,054.5–8,309.17 ms

Google AI Studiogoogle-ai-studio/flex

1,625.5–3,297.07 ms

All latency percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/us	1,074 ms	1,196 ms	1,777.4 ms	2,318 ms
Googlegoogle-vertex/global/flex	10,509 ms	12,536.25 ms	28,181.3 ms	53,720.46 ms
Googlegoogle-vertex/global/priority	3,051 ms	3,738.5 ms	5,222.4 ms	7,287.88 ms
Googlegoogle-vertex/global	1,310 ms	1,865 ms	2,970.4 ms	8,317.62 ms
Google AI Studiogoogle-ai-studio/priority	3,054.5 ms	3,838 ms	4,937.2 ms	8,309.17 ms
Google AI Studiogoogle-ai-studio/flex	1,625.5 ms	2,162 ms	2,631.3 ms	3,297.07 ms
Google AI Studiogoogle-ai-studio	1,139 ms	1,345 ms	1,854 ms	4,835.02 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Googlegoogle-vertex/us

77–122.48 t/s

Googlegoogle-vertex/global/flex

47–190.08 t/s

Googlegoogle-vertex/global/priority

149–271.36 t/s

Googlegoogle-vertex/global

132–255 t/s

Google AI Studiogoogle-ai-studio/priority

147.5–238.1 t/s

Google AI Studiogoogle-ai-studio/flex

155–248.6 t/s

All throughput percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/us	77 t/s	97.5 t/s	115.7 t/s	122.48 t/s
Googlegoogle-vertex/global/flex	47 t/s	55.25 t/s	71.7 t/s	190.08 t/s
Googlegoogle-vertex/global/priority	149 t/s	177 t/s	208.8 t/s	271.36 t/s
Googlegoogle-vertex/global	132 t/s	178 t/s	207 t/s	255 t/s
Google AI Studiogoogle-ai-studio/priority	147.5 t/s	178 t/s	193.1 t/s	238.1 t/s
Google AI Studiogoogle-ai-studio/flex	155 t/s	178 t/s	211 t/s	248.6 t/s
Google AI Studiogoogle-ai-studio	74 t/s	115 t/s	151 t/s	220 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 7 endpoints

Endpoint5 minutes30 minutes24 hours

Googlegoogle-vertex/usObserved Oct 4, 2026, 11:31 AM UTC

—

100%

Googlegoogle-vertex/global/flexObserved Oct 4, 2026, 11:31 AM UTC

—

99.04%

97.4%

Googlegoogle-vertex/global/priorityObserved Oct 4, 2026, 11:31 AM UTC

100%

99.84%

Googlegoogle-vertex/globalObserved Oct 4, 2026, 11:31 AM UTC

99.63%

99.57%

99.93%

Google AI Studiogoogle-ai-studio/priorityObserved Oct 4, 2026, 11:31 AM UTC

—

100%

99.87%

Google AI Studiogoogle-ai-studio/flexObserved Oct 4, 2026, 11:31 AM UTC

—

100%

Google AI Studiogoogle-ai-studioObserved Oct 4, 2026, 11:31 AM UTC

100%

99.94%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

google/gemini-3.6-flashObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 70

Coding

69.2

Agentic

Intelligence

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,180	47.8%	13
agents	androidnative	1,217	53.7%	11
agents	fullstack	1,179	44.3%	21
agents	htmlslides	1,148	41.9%	17
agents	mobileapps	1,198	50.6%	16
agents	python-pptxslides	1,146	38.8%	24
agents	webapps	1,187	45.4%	22
models	3d	1,289	53.2%	18
models	asciiart	1,289	56.9%	7
models	codecategories	1,295	53.5%	16
models	dataviz	1,302	53.4%	11
models	gamedev	1,275	51.1%	25
models	uicomponent	1,306	54.4%	14
models	website	1,306	55.4%	11

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineGoogle: Gemini 3.6 Flash

74.667%

gpqa diamondGoogle: Gemini 3.6 Flash

92.649%

Evaluation	Configuration	Source	Results	Details
models · dataviz	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,302 Elo	Details
models · gamedev	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,275 Elo	Details
Composite indices	Gemini 3.6 Flash (high)google/gemini-3.6-flash-20260721	Artificial Analysis	Intelligence 34 · Coding 69.2 · Agentic 29	Details
models · 3d	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,289 Elo	Details
models · website	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,306 Elo	Details
models · uicomponent	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,306 Elo	Details
tau bench verified airline	Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	OpenRouter	74.667%	Details
models · codecategories	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,295 Elo	Details
gpqa diamond	Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	OpenRouter	92.649%	Details
models · asciiart	Gemini 3.6 Flashgoogle/gemini-3.6-flash-20260721	Design Arena	1,289 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	google/gemini-3.6-flash-20260721	2–9 turns	$0.017476	Details
Hermes Agent	google/gemini-3.6-flash-20260721	10–49 turns	$0.157444	Details
Hermes Agent	google/gemini-3.6-flash-20260721	1 turn	$0.001588	Details
Hermes Agent	google/gemini-3.6-flash-20260721	50+ turns	$0.764896	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage6,729,210,272,681 reported tokens · 38 days with observations

909B0

2026-07-22
38,634,840,403 tokens

2026-07-23
34,178,705,666 tokens

2026-07-24
44,460,169,266 tokens

2026-07-25
62,384,454,570 tokens

2026-07-26
50,565,244,364 tokens

2026-07-27
54,068,532,104 tokens

2026-07-28
37,958,848,021 tokens

2026-07-29
35,657,767,963 tokens

2026-07-30
68,246,634,162 tokens

2026-07-31
92,922,352,942 tokens

2026-08-01
68,307,516,973 tokens

2026-08-02
69,201,475,926 tokens

2026-08-03
62,719,847,661 tokens

2026-08-04
48,414,424,500 tokens

2026-08-05
747,656,880,807 tokens

2026-08-06
909,202,542,424 tokens

2026-08-07
420,429,569,830 tokens

2026-08-08
78,367,119,883 tokens

2026-08-09
61,998,391,986 tokens

2026-08-10
58,847,587,697 tokens

2026-08-11
179,113,275,687 tokens

2026-08-12
377,551,111,706 tokens

2026-08-13
524,139,207,266 tokens

2026-08-14
511,371,240,396 tokens

2026-08-15
132,530,648,115 tokens

2026-08-16
500,450,230,972 tokens

2026-08-17
543,487,918,358 tokens

2026-08-18
156,843,538,241 tokens

2026-08-19
62,174,141,082 tokens

2026-08-20
97,325,380,712 tokens

2026-08-21
98,173,104,729 tokens

2026-08-22
21,447,664,894 tokens

2026-08-23
36,415,228,212 tokens

2026-08-24
67,032,767,625 tokens

2026-08-25
241,478,729,046 tokens

2026-08-28
66,700,520,935 tokens

2026-08-31
35,462,436,878 tokens

2026-09-01
33,290,220,679 tokens

Jul 6, 2026Oct 3, 2026

Daily observations · 38 days

Date (UTC)	Reported tokens	Reported routes
Sep 1, 2026	33,290,220,679	1
Aug 31, 2026	35,462,436,878	1
Aug 28, 2026	66,700,520,935	1
Aug 25, 2026	241,478,729,046	1
Aug 24, 2026	67,032,767,625	1
Aug 23, 2026	36,415,228,212	1
Aug 22, 2026	21,447,664,894	1
Aug 21, 2026	98,173,104,729	1
Aug 20, 2026	97,325,380,712	1
Aug 19, 2026	62,174,141,082	1
Aug 18, 2026	156,843,538,241	1
Aug 17, 2026	543,487,918,358	1
Aug 16, 2026	500,450,230,972	1
Aug 15, 2026	132,530,648,115	1
Aug 14, 2026	511,371,240,396	1
Aug 13, 2026	524,139,207,266	1
Aug 12, 2026	377,551,111,706	1
Aug 11, 2026	179,113,275,687	1
Aug 10, 2026	58,847,587,697	1
Aug 9, 2026	61,998,391,986	1
Aug 8, 2026	78,367,119,883	1
Aug 7, 2026	420,429,569,830	1
Aug 6, 2026	909,202,542,424	1
Aug 5, 2026	747,656,880,807	1
Aug 4, 2026	48,414,424,500	1
Aug 3, 2026	62,719,847,661	1
Aug 2, 2026	69,201,475,926	1
Aug 1, 2026	68,307,516,973	1
Jul 31, 2026	92,922,352,942	1
Jul 30, 2026	68,246,634,162	1
Jul 29, 2026	35,657,767,963	1
Jul 28, 2026	37,958,848,021	1
Jul 27, 2026	54,068,532,104	1
Jul 26, 2026	50,565,244,364	1
Jul 25, 2026	62,384,454,570	1
Jul 24, 2026	44,460,169,266	1
Jul 23, 2026	34,178,705,666	1
Jul 22, 2026	38,634,840,403	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

google/gemini-3.6-flashObserved Oct 4, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 65,536
Tokenizer: Gemini
Input: text, image, video, file, audio
Output: text
Moderation: No
Added to OpenRouter: 2026-07-21

Base URLhttps://openrouter.ai/api/v1

Model IDgoogle/gemini-3.6-flash

Version IDgoogle/gemini-3.6-flash-20260721

Reasoning

Required: Yes
Enabled by default: Yes
Default effort: medium
Supported efforts: high, medium, low, minimal

Supported parameters

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

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Gemini 3.6 Flash cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 3.6 Flash?

There are 36 cataloged offers across 26 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,048,576 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 4da8546bd578
Sep 12, 2026 · edab2ed3dadd