Gemini 3.5 Flash

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.

Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

google/gemini-3.5-flash

Organization: Google
Family: gemini-flash
Providers: 36
Context: 1,048,576
Output limit: 65,536
Knowledge: 2025-01
Release: 2026-05-19
Updated: —
Weights: Closed
Input: text, image/png, image/jpeg, image/webp, image/heic, image/heif, video/mp4, video/mpeg, video/mov, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp, audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm, application/pdf
Output: text
Capabilities: —

Providers

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

48 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-3.5-flash-thinking	1,048,576	65,536	— / —	—	—	—	View
302.AI	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Abacus	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
AIHubMix	gemini-3.5-flash	1,000,000	64,000	— / —	—	—	—	View
Cloudflare AI Gateway	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
CommandCode	google/gemini-3.5-flash	1,000,000	65,536	— / —	—	—	—	View
Cortecs	gemini-3.5-flash	1,048,576	65,535	— / —	—	—	—	View
CrossModel	gemini/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Databricks	databricks-gemini-3-5-flash	1,048,576	65,536	— / —	—	—	—	View
DevPass (LLM Gateway)	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.5-flash@us	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.5-flash@eu	1,048,576	65,536	— / —	—	—	—	View
FastRouter	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
GitHub Copilot	gemini-3.5-flash	200,000	64,000	— / —	—	—	—	View
Impossibl	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Kenari	gemini-3-5-flash	1,048,576	65,536	— / —	—	—	—	View
Kilo Gateway	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
LLM Gateway	google-vertex/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Merge Gateway	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.5-flash-thinking	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
NEAR AI Cloud	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Neon	gemini-3-5-flash	1,048,576	65,536	— / —	—	—	—	View
Ofox	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
OpenCode	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Googlevia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$1.65 / $9.90	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$1.50 / $9.00	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$0.75 / $4.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$2.70 / $16.20	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$2.70 / $16.20	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$1.50 / $9.00	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.5-flash unknown	1,048,576	65,536	$0.75 / $4.50	Yes	Yes	Yes	View
Opper	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
OrcaRouter	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Poe	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Prime Inference	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Requesty	gemini-3.5-flash@eu	1,048,576	65,535	— / —	—	—	—	View
Requesty	gemini-3.5-flash	1,048,576	65,535	— / —	—	—	—	View
SAP AI Core	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Tempr Gateway	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
UnoRouter	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Venice AI	gemini-3-5-flash	1,000,000	65,536	— / —	—	—	—	View
Vercel AI Gateway	google/gemini-3.5-flash	1,000,000	64,000	— / —	—	—	—	View
Vertex	gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	View
Xpersona	gemini-3.5-flash	1,000,000	128,000	— / —	—	—	—	View
ZenMux	google/gemini-3.5-flash	1,048,576	65,536	— / —	—	—	—	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$0.75Per 1M input tokens

Output from$4.50Per 1M output tokens

Available offers48Across 36 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

$0.75$4.50

Google AI Studiogoogle-ai-studio/flex

$0.75$4.50

Googlegoogle-vertex/global

$1.50$9.00

Google AI Studiogoogle-ai-studio

$1.50$9.00

Googlegoogle-vertex/us

$1.65$9.90

Googlegoogle-vertex/global/priority

$2.70$16.20

Google AI Studiogoogle-ai-studio/priority

$2.70$16.20

google/gemini-3.5-flashObserved Oct 10, 2026, 11:31 AM UTC

Input: $1.50
Output: $9.00
Cache read: $0.15
Cache write: $0.083333

Additional fees and pricing conditions

audio: $0.000003 / audio token
image: $0.0000015 / image
web search: $0.014 / search
input audio cache: $0.0000003 / audio token
internal reasoning: $0.000009 / 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	$1.65	$9.90	$0.165	$0.083333
Googlegoogle-vertex/global	$1.50	$9.00	$0.15	$0.083333
Googlegoogle-vertex/global/flex	$0.75	$4.50	$0.075	$0.041667
Googlegoogle-vertex/global/priority	$2.70	$16.20	$0.27	$0.15
Google AI Studiogoogle-ai-studio/priority	$2.70	$16.20	$0.27	$0.15
Google AI Studiogoogle-ai-studio	$1.50	$9.00	$0.15	$0.083333
Google AI Studiogoogle-ai-studio/flex	$0.75	$4.50	$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 · 5 endpoints

P50P75P90P99

Googlegoogle-vertex/global

1,648–5,480.97 ms

Googlegoogle-vertex/global/flex

13,034–76,640.14 ms

Googlegoogle-vertex/global/priority

1,426–2,174.59 ms

Google AI Studiogoogle-ai-studio

1,361.5–14,222.72 ms

Google AI Studiogoogle-ai-studio/flex

1,126–4,035 ms

All latency percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	1,648 ms	2,261.25 ms	2,759 ms	5,480.97 ms
Googlegoogle-vertex/global/flex	13,034 ms	13,445.5 ms	19,246 ms	76,640.14 ms
Googlegoogle-vertex/global/priority	1,426 ms	1,598.75 ms	1,768.7 ms	2,174.59 ms
Google AI Studiogoogle-ai-studio	1,361.5 ms	2,209.5 ms	3,213.8 ms	14,222.72 ms
Google AI Studiogoogle-ai-studio/flex	1,126 ms	1,309 ms	1,740 ms	4,035 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 5 endpoints

P50P75P90P99

Googlegoogle-vertex/global

98–229 t/s

Googlegoogle-vertex/global/flex

21–34.81 t/s

Googlegoogle-vertex/global/priority

133.5–205.42 t/s

Google AI Studiogoogle-ai-studio

141–216.28 t/s

Google AI Studiogoogle-ai-studio/flex

107–157 t/s

All throughput percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	98 t/s	140 t/s	173 t/s	229 t/s
Googlegoogle-vertex/global/flex	21 t/s	24 t/s	29 t/s	34.81 t/s
Googlegoogle-vertex/global/priority	133.5 t/s	173.25 t/s	186 t/s	205.42 t/s
Google AI Studiogoogle-ai-studio	141 t/s	157 t/s	177 t/s	216.28 t/s
Google AI Studiogoogle-ai-studio/flex	107 t/s	114 t/s	121 t/s	157 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 10, 2026, 11:31 AM UTC

—

100%

Googlegoogle-vertex/globalObserved Oct 10, 2026, 11:31 AM UTC

100%

Googlegoogle-vertex/global/flexObserved Oct 10, 2026, 11:31 AM UTC

—

100%

Googlegoogle-vertex/global/priorityObserved Oct 10, 2026, 11:31 AM UTC

100%

Google AI Studiogoogle-ai-studio/priorityObserved Oct 10, 2026, 11:31 AM UTC

—

100%

Google AI Studiogoogle-ai-studioObserved Oct 10, 2026, 11:31 AM UTC

100%

95.14%

Google AI Studiogoogle-ai-studio/flexObserved Oct 10, 2026, 11:31 AM UTC

100%

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-3.5-flashObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 40

Intelligence

33.6

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,180	55.4%	12
agents	agentichtmlslides	1,162	45.8%	6
agents	agenticslides	1,244	57.5%	3
agents	agenticslides(html)	1,162	45.7%	6
agents	agenticslides(python-pptx)	1,242	57.8%	2
agents	androidnative	1,199	57.7%	14
agents	fullstack	1,197	56.2%	18
agents	godotgamedev	1,098	43%	30
agents	htmlslides	1,142	46.5%	19
agents	mobileapps	1,173	51.2%	21
agents	pptxslides	1,244	57.7%	2
agents	python-pptxslides	1,247	57.4%	9
agents	webapps	1,196	52.6%	20
models	3d	1,250	56.3%	29
models	asciiart	1,259	58.9%	16
models	codecategories	1,268	54.2%	29
models	dataviz	1,238	52.9%	38
models	gamedev	1,269	52.9%	27
models	svg	1,253	58.5%	13
models	uicomponent	1,277	54.8%	26
models	website	1,269	53.8%	30

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 3.5 Flash

73.111%

gpqa diamondGoogle: Gemini 3.5 Flash

92.593%

Evaluation	Configuration	Source	Results	Details
models · dataviz	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,236 Elo	Details
models · website	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,267 Elo	Details
models · asciiart	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,254 Elo	Details
Composite indices	Gemini 3.5 Flash (Medium)google/gemini-3.5-flash-20260519	Artificial Analysis	Intelligence 33.6 · Coding — · Agentic —	Details
models · gamedev	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,265 Elo	Details
models · svg	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,254 Elo	Details
tau bench verified airline	Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	OpenRouter	73.111%	Details
models · codecategories	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,266 Elo	Details
models · 3d	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,245 Elo	Details
models · uicomponent	Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	Design Arena	1,268 Elo	Details
gpqa diamond	Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash-20260519	OpenRouter	92.593%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

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

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	google/gemini-3.5-flash-20260519	1 turn	$0.012381	Details
Hermes Agent	google/gemini-3.5-flash-20260519	50+ turns	$1.810376	Details
Hermes Agent	google/gemini-3.5-flash-20260519	2–9 turns	$0.065211	Details
Hermes Agent	google/gemini-3.5-flash-20260519	10–49 turns	$0.4728	Details

Source: OpenRouter, as of Oct 20, 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 usage562,074,894,964 reported tokens · 19 days with observations

44B0

2026-07-27
37,374,177,266 tokens

2026-07-28
34,630,437,038 tokens

2026-07-29
43,912,722,327 tokens

2026-07-30
37,756,783,782 tokens

2026-07-31
37,345,548,630 tokens

2026-08-01
20,108,024,465 tokens

2026-08-02
20,616,854,761 tokens

2026-08-03
28,449,712,471 tokens

2026-08-04
34,461,628,211 tokens

2026-08-05
29,012,022,228 tokens

2026-08-06
26,634,814,919 tokens

2026-08-07
26,606,441,121 tokens

2026-08-09
22,807,197,212 tokens

2026-08-10
26,751,296,692 tokens

2026-08-13
30,828,881,987 tokens

2026-08-14
28,281,343,660 tokens

2026-08-15
23,049,297,858 tokens

2026-08-16
24,834,434,853 tokens

2026-08-17
28,613,275,483 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 19 days

Date (UTC)	Reported tokens	Reported routes
Aug 17, 2026	28,613,275,483	1
Aug 16, 2026	24,834,434,853	1
Aug 15, 2026	23,049,297,858	1
Aug 14, 2026	28,281,343,660	1
Aug 13, 2026	30,828,881,987	1
Aug 10, 2026	26,751,296,692	1
Aug 9, 2026	22,807,197,212	1
Aug 7, 2026	26,606,441,121	1
Aug 6, 2026	26,634,814,919	1
Aug 5, 2026	29,012,022,228	1
Aug 4, 2026	34,461,628,211	1
Aug 3, 2026	28,449,712,471	1
Aug 2, 2026	20,616,854,761	1
Aug 1, 2026	20,108,024,465	1
Jul 31, 2026	37,345,548,630	1
Jul 30, 2026	37,756,783,782	1
Jul 29, 2026	43,912,722,327	1
Jul 28, 2026	34,630,437,038	1
Jul 27, 2026	37,374,177,266	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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-3.5-flashObserved Oct 10, 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
Knowledge cutoff: 2025-01-01
Added to OpenRouter: 2026-05-19

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

Model IDgoogle/gemini-3.5-flash

Version IDgoogle/gemini-3.5-flash-20260519

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 3.5 Flash cost?

Listed rates start at $0.75 per million input tokens and $4.50 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 3.5 Flash?

There are 48 cataloged offers across 36 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: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 3 recorded revisions

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

Oct 20, 2026 · 8d0b85dfc398
Sep 14, 2026 · dfe90f945606
Sep 12, 2026 · 371463e8b722