Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

google/gemini-3.7-flash

Organization: Google
Family: gemini-flash
Providers: 31
Context: 1,048,576
Output limit: 65,536
Knowledge: 2026-03
Release: 2026-08-13
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.

40 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Abacus	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
AIHubMix	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
AI/ML API	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Cloudflare AI Gateway	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
CommandCode	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Cortecs	gemini-3.7-flash	1,048,576	65,535	— / —	—	—	—	View
CrossModel	gemini/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
DevPass (LLM Gateway)	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.7-flash@us	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.7-flash@eu	1,048,576	65,536	— / —	—	—	—	View
GitHub Copilot	gemini-3.7-flash	1,000,000	64,000	— / —	—	—	—	View
Google	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Kenari	gemini-3-7-flash	1,048,576	65,536	— / —	—	—	—	View
Kilo Gateway	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
LLM Gateway	google-vertex/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Merge Gateway	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Neon	gemini-3-7-flash	1,048,576	65,536	— / —	—	—	—	View
Ofox	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
OpenCode	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Googlevia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.7-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Opper	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Perplexity Agent	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Poe	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Prime Inference	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Requesty	gemini-3.7-flash	1,048,576	65,535	— / —	—	—	—	View
Requesty	gemini-3.7-flash@eu	1,048,576	65,535	— / —	—	—	—	View
Tempr Gateway	google/gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Venice AI	gemini-3-7-flash	1,000,000	65,536	— / —	—	—	—	View
Vercel AI Gateway	google/gemini-3.7-flash	1,000,000	65,535	— / —	—	—	—	View
Vertex	gemini-3.7-flash	1,048,576	65,536	— / —	—	—	—	View
Vivgrid	gemini-3.7-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$0.375Per 1M input tokens

Output from$1.875Per 1M output tokens

Available offers40Across 31 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 · 6 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/global/priority

$1.35$6.75

Google AI Studiogoogle-ai-studio/priority

$1.35$6.75

google/gemini-3.7-flashObserved Oct 10, 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/global/priority	$1.35	$6.75	$0.135	$0.075
Googlegoogle-vertex/global/flex	$0.375	$1.875	$0.0375	$0.020833
Googlegoogle-vertex/global	$0.75	$3.75	$0.075	$0.041667
Google AI Studiogoogle-ai-studio	$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

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/global/priority

2,007–5,089.76 ms

Googlegoogle-vertex/global/flex

13,977–246,964.94 ms

Googlegoogle-vertex/global

2,164–8,811.09 ms

Google AI Studiogoogle-ai-studio

2,249–18,895.35 ms

Google AI Studiogoogle-ai-studio/priority

1,573–2,737.92 ms

Google AI Studiogoogle-ai-studio/flex

1,512–8,550.18 ms

All latency percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global/priority	2,007 ms	2,425 ms	3,297.6 ms	5,089.76 ms
Googlegoogle-vertex/global/flex	13,977 ms	16,329.5 ms	32,095.6 ms	246,964.94 ms
Googlegoogle-vertex/global	2,164 ms	2,621 ms	3,682 ms	8,811.09 ms
Google AI Studiogoogle-ai-studio	2,249 ms	3,315.25 ms	4,801.9 ms	18,895.35 ms
Google AI Studiogoogle-ai-studio/priority	1,573 ms	1,997 ms	2,352 ms	2,737.92 ms
Google AI Studiogoogle-ai-studio/flex	1,512 ms	2,336.25 ms	3,226.9 ms	8,550.18 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Googlegoogle-vertex/global/priority

91–195.99 t/s

Googlegoogle-vertex/global/flex

44–146.48 t/s

Googlegoogle-vertex/global

98–203 t/s

Google AI Studiogoogle-ai-studio

98–341 t/s

Google AI Studiogoogle-ai-studio/priority

106–216.6 t/s

Google AI Studiogoogle-ai-studio/flex

92–190 t/s

All throughput percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global/priority	91 t/s	126.5 t/s	156.3 t/s	195.99 t/s
Googlegoogle-vertex/global/flex	44 t/s	83.5 t/s	109 t/s	146.48 t/s
Googlegoogle-vertex/global	98 t/s	129 t/s	162 t/s	203 t/s
Google AI Studiogoogle-ai-studio	98 t/s	128 t/s	259 t/s	341 t/s
Google AI Studiogoogle-ai-studio/priority	106 t/s	136 t/s	182 t/s	216.6 t/s
Google AI Studiogoogle-ai-studio/flex	92 t/s	115 t/s	144 t/s	190 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 · 6 endpoints

Endpoint5 minutes30 minutes24 hours

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

—

100%

99.77%

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

100%

98.18%

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

100%

99.79%

Google AI Studiogoogle-ai-studioObserved 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-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-3.7-flashObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 80

Coding

71.5

Intelligence

39.6

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,235	52.1%	5
agents	androidnative	1,255	53.3%	6
agents	fullstack	1,209	43.5%	16
agents	godotgamedev	1,264	50.8%	6
agents	mobileapps	1,227	52.9%	8
agents	webapps	1,214	46.6%	15
models	3d	1,314	53.8%	12
models	asciiart	1,285	56.5%	6
models	codecategories	1,313	54%	10
models	dataviz	1,322	55.5%	10
models	gamedev	1,329	53.7%	9
models	svg	1,285	53.4%	12
models	uicomponent	1,304	52.3%	14
models	website	1,308	54%	9

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 3.7 Flash

78.311%

gpqa diamondGoogle: Gemini 3.7 Flash

93.853%

Evaluation	Configuration	Source	Results	Details
models · svg	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,283 Elo	Details
models · website	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,303 Elo	Details
models · codecategories	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,308 Elo	Details
models · 3d	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,309 Elo	Details
models · uicomponent	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,293 Elo	Details
Composite indices	Gemini 3.7 Flash (Medium)google/gemini-3.7-flash-20260813	Artificial Analysis	Intelligence 39.6 · Coding 71.5 · Agentic —	Details
models · asciiart	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,278 Elo	Details
tau bench verified airline	Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	OpenRouter	78.311%	Details
models · dataviz	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,317 Elo	Details
models · gamedev	Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	Design Arena	1,320 Elo	Details
gpqa diamond	Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash-20260813	OpenRouter	93.853%	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-3.7-flash-20260813	10–49 turns	$0.197032	Details
Hermes Agent	google/gemini-3.7-flash-20260813	2–9 turns	$0.031119	Details
Hermes Agent	google/gemini-3.7-flash-20260813	1 turn	$0.006672	Details
Hermes Agent	google/gemini-3.7-flash-20260813	50+ turns	$1.131162	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 usage11,340,216,601,359 reported tokens · 65 days with observations

1.2T0

2026-08-14
117,450,817,391 tokens

2026-08-15
127,900,176,136 tokens

2026-08-16
142,660,754,880 tokens

2026-08-17
192,291,618,818 tokens

2026-08-18
229,195,983,746 tokens

2026-08-19
273,478,978,191 tokens

2026-08-20
267,644,442,628 tokens

2026-08-21
254,586,240,886 tokens

2026-08-22
219,430,107,732 tokens

2026-08-23
360,938,063,111 tokens

2026-08-24
416,024,825,759 tokens

2026-08-25
785,149,865,124 tokens

2026-08-26
1,178,197,291,424 tokens

2026-08-27
613,468,921,106 tokens

2026-08-28
353,600,982,632 tokens

2026-08-29
341,536,549,507 tokens

2026-08-30
260,140,381,548 tokens

2026-08-31
318,496,881,766 tokens

2026-09-01
444,021,991,095 tokens

2026-09-02
499,024,261,857 tokens

2026-09-03
409,934,459,938 tokens

2026-09-04
218,760,164,884 tokens

2026-09-05
113,687,315,931 tokens

2026-09-06
96,162,418,672 tokens

2026-09-07
116,618,262,320 tokens

2026-09-08
131,035,897,559 tokens

2026-09-09
150,667,700,079 tokens

2026-09-10
107,772,207,081 tokens

2026-09-11
99,807,686,408 tokens

2026-09-12
98,434,348,224 tokens

2026-09-13
101,100,471,642 tokens

2026-09-14
93,417,030,853 tokens

2026-09-15
84,352,906,738 tokens

2026-09-16
87,906,048,452 tokens

2026-09-17
78,561,362,057 tokens

2026-09-18
87,221,828,444 tokens

2026-09-19
65,590,548,682 tokens

2026-09-20
64,558,555,203 tokens

2026-09-21
82,266,595,667 tokens

2026-09-22
84,017,239,932 tokens

2026-09-23
73,222,557,387 tokens

2026-09-24
69,670,521,555 tokens

2026-09-25
76,892,117,813 tokens

2026-09-26
56,090,028,567 tokens

2026-09-27
52,647,939,733 tokens

2026-09-28
71,147,754,463 tokens

2026-09-29
84,937,204,920 tokens

2026-09-30
70,957,577,766 tokens

2026-10-01
68,068,281,158 tokens

2026-10-02
74,561,914,556 tokens

2026-10-03
50,774,248,638 tokens

2026-10-04
48,780,998,902 tokens

2026-10-05
62,675,551,684 tokens

2026-10-06
67,773,729,715 tokens

2026-10-07
65,372,965,031 tokens

2026-10-08
66,035,325,706 tokens

2026-10-09
66,313,551,944 tokens

2026-10-14
58,060,890,483 tokens

2026-10-15
58,957,004,626 tokens

2026-10-16
60,275,406,948 tokens

2026-10-17
45,606,283,402 tokens

2026-10-18
42,682,030,119 tokens

2026-10-19
61,333,519,841 tokens

2026-10-21
57,354,224,820 tokens

2026-10-22
62,912,787,479 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 65 days

Date (UTC)	Reported tokens	Reported routes
Oct 22, 2026	62,912,787,479	1
Oct 21, 2026	57,354,224,820	1
Oct 19, 2026	61,333,519,841	1
Oct 18, 2026	42,682,030,119	1
Oct 17, 2026	45,606,283,402	1
Oct 16, 2026	60,275,406,948	1
Oct 15, 2026	58,957,004,626	1
Oct 14, 2026	58,060,890,483	1
Oct 9, 2026	66,313,551,944	1
Oct 8, 2026	66,035,325,706	1
Oct 7, 2026	65,372,965,031	1
Oct 6, 2026	67,773,729,715	1
Oct 5, 2026	62,675,551,684	1
Oct 4, 2026	48,780,998,902	1
Oct 3, 2026	50,774,248,638	1
Oct 2, 2026	74,561,914,556	1
Oct 1, 2026	68,068,281,158	1
Sep 30, 2026	70,957,577,766	1
Sep 29, 2026	84,937,204,920	1
Sep 28, 2026	71,147,754,463	1
Sep 27, 2026	52,647,939,733	1
Sep 26, 2026	56,090,028,567	1
Sep 25, 2026	76,892,117,813	1
Sep 24, 2026	69,670,521,555	1
Sep 23, 2026	73,222,557,387	1
Sep 22, 2026	84,017,239,932	1
Sep 21, 2026	82,266,595,667	1
Sep 20, 2026	64,558,555,203	1
Sep 19, 2026	65,590,548,682	1
Sep 18, 2026	87,221,828,444	1
Sep 17, 2026	78,561,362,057	1
Sep 16, 2026	87,906,048,452	1
Sep 15, 2026	84,352,906,738	1
Sep 14, 2026	93,417,030,853	1
Sep 13, 2026	101,100,471,642	1
Sep 12, 2026	98,434,348,224	1
Sep 11, 2026	99,807,686,408	1
Sep 10, 2026	107,772,207,081	1
Sep 9, 2026	150,667,700,079	1
Sep 8, 2026	131,035,897,559	1
Sep 7, 2026	116,618,262,320	1
Sep 6, 2026	96,162,418,672	1
Sep 5, 2026	113,687,315,931	1
Sep 4, 2026	218,760,164,884	1
Sep 3, 2026	409,934,459,938	1
Sep 2, 2026	499,024,261,857	1
Sep 1, 2026	444,021,991,095	1
Aug 31, 2026	318,496,881,766	1
Aug 30, 2026	260,140,381,548	1
Aug 29, 2026	341,536,549,507	1
Aug 28, 2026	353,600,982,632	1
Aug 27, 2026	613,468,921,106	1
Aug 26, 2026	1,178,197,291,424	1
Aug 25, 2026	785,149,865,124	1
Aug 24, 2026	416,024,825,759	1
Aug 23, 2026	360,938,063,111	1
Aug 22, 2026	219,430,107,732	1
Aug 21, 2026	254,586,240,886	1
Aug 20, 2026	267,644,442,628	1
Aug 19, 2026	273,478,978,191	1
Aug 18, 2026	229,195,983,746	1
Aug 17, 2026	192,291,618,818	1
Aug 16, 2026	142,660,754,880	1
Aug 15, 2026	127,900,176,136	1
Aug 14, 2026	117,450,817,391	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-3.7-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
Added to OpenRouter: 2026-08-13

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

Model IDgoogle/gemini-3.7-flash

Version IDgoogle/gemini-3.7-flash-20260813

Reasoning

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

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 3.7 Flash cost?

Listed rates start at $0.375 per million input tokens and $1.875 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 3.7 Flash?

There are 40 cataloged offers across 31 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 · 40ff04103a55
Sep 14, 2026 · 43d4eb5827de
Sep 12, 2026 · f4fb3b962e2b