Gemini 2.5 Flash

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).

google/gemini-2.5-flash

Organization: Google
Family: gemini-flash
Providers: 32
Context: 1,048,576
Output limit: 65,536
Knowledge: 2025-01
Release: 2025-06-17
Updated: —
Weights: Closed
Input: text, image/png, image/jpeg, image/webp, image/heic, image/heif, 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, video/mp4, video/mpeg, video/mov, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp, application/pdf
Output: text
Capabilities: —

Providers

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

39 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-2.5-flash-nothink	1,000,000	65,536	— / —	—	—	—	View
302.AI	gemini-2.5-flash	1,000,000	65,536	— / —	—	—	—	View
Abacus	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
AIHubMix	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
AnyAPI	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Auriko	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Cloudflare AI Gateway	google/gemini-2.5-flash	1,000,000	65,536	— / —	—	—	—	View
Cortecs	gemini-2.5-flash	1,048,576	65,535	— / —	—	—	—	View
CrossModel	gemini/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Databricks	databricks-gemini-2-5-flash	1,048,576	65,536	— / —	—	—	—	View
FastRouter	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
FrogBot	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Google	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Helicone	gemini-2.5-flash	1,048,576	65,535	— / —	—	—	—	View
Impossibl	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Jiekou.AI	gemini-2.5-flash	1,048,576	65,535	— / —	—	—	—	View
Kenari	gemini-2-5-flash	1,048,576	65,536	— / —	—	—	—	View
Kilo Gateway	google/gemini-2.5-flash	1,048,576	65,535	— / —	—	—	—	View
Merge Gateway	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Modelis	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
NEAR AI Cloud	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Ofox	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Googlevia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.30 / $2.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.30 / $2.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.30 / $2.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.54 / $4.50	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.15 / $1.25	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.30 / $2.50	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-2.5-flash unknown	1,048,576	65,535	$0.54 / $4.50	Yes	Yes	Yes	View
OrcaRouter	google/gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Poe	google/gemini-2.5-flash	1,065,535	65,535	— / —	—	—	—	View
QiHang	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Qiniu	gemini-2.5-flash	1,048,576	64,000	— / —	—	—	—	View
Requesty	gemini-2.5-flash@eu	1,048,576	65,535	— / —	—	—	—	View
SAP AI Core	gemini-2.5-flash	1,048,576	65,536	— / —	—	—	—	View
Standard Compute	google/gemini-2.5-flash	1,048,576	50,000	— / —	—	—	—	View
Vercel AI Gateway	google/gemini-2.5-flash	1,000,000	65,535	— / —	—	—	—	View
ZenMux	google/gemini-2.5-flash	1,048,000	65,535	— / —	—	—	—	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$0.15Per 1M input tokens

Output from$1.25Per 1M output tokens

Available offers39Across 32 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

Google AI Studiogoogle-ai-studio/flex

$0.15$1.25

Googlegoogle-vertex/eu

$0.30$2.50

Googlegoogle-vertex

$0.30$2.50

Googlegoogle-vertex/global

$0.30$2.50

Google AI Studiogoogle-ai-studio

$0.30$2.50

Googlegoogle-vertex/global/priority

$0.54$4.50

Google AI Studiogoogle-ai-studio/priority

$0.54$4.50

google/gemini-2.5-flashObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.30
Output: $2.50
Cache read: $0.03
Cache write: $0.083333

Additional fees and pricing conditions

audio: $0.000001 / audio token
image: $0.0000003 / image
web search: $0.014 / search
input audio cache: $0.0000001 / audio token
internal reasoning: $0.0000025 / reasoning token

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Googlegoogle-vertex/eu	$0.30	$2.50	$0.03	$0.083333
Googlegoogle-vertex	$0.30	$2.50	$0.03	$0.083333
Googlegoogle-vertex/global	$0.30	$2.50	$0.03	$0.083333
Googlegoogle-vertex/global/priority	$0.54	$4.50	$0.054	$0.15
Google AI Studiogoogle-ai-studio/flex	$0.15	$1.25	$0.015	$0.041667
Google AI Studiogoogle-ai-studio	$0.30	$2.50	$0.03	$0.083333
Google AI Studiogoogle-ai-studio/priority	$0.54	$4.50	$0.054	$0.15

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/eu

741–4,066.8 ms

Googlegoogle-vertex

1,174.5–10,442 ms

Googlegoogle-vertex/global

1,038–4,688.36 ms

Googlegoogle-vertex/global/priority

825–2,893.98 ms

Google AI Studiogoogle-ai-studio/flex

489.5–1,956.9 ms

Google AI Studiogoogle-ai-studio

534–15,502.53 ms

All latency percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/eu	741 ms	933 ms	1,512.8 ms	4,066.8 ms
Googlegoogle-vertex	1,174.5 ms	1,622.75 ms	4,316 ms	10,442 ms
Googlegoogle-vertex/global	1,038 ms	1,348 ms	1,751.9 ms	4,688.36 ms
Googlegoogle-vertex/global/priority	825 ms	994 ms	1,160 ms	2,893.98 ms
Google AI Studiogoogle-ai-studio/flex	489.5 ms	662.25 ms	1,512.9 ms	1,956.9 ms
Google AI Studiogoogle-ai-studio	534 ms	942 ms	1,463 ms	15,502.53 ms
Google AI Studiogoogle-ai-studio/priority	784 ms	833 ms	862.4 ms	880.04 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Googlegoogle-vertex/eu

92–212 t/s

Googlegoogle-vertex

93–224.92 t/s

Googlegoogle-vertex/global

85–242 t/s

Googlegoogle-vertex/global/priority

82–158.66 t/s

Google AI Studiogoogle-ai-studio/flex

152–219 t/s

Google AI Studiogoogle-ai-studio

106–241 t/s

All throughput percentiles 7 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/eu	92 t/s	136.25 t/s	162 t/s	212 t/s
Googlegoogle-vertex	93 t/s	128 t/s	159 t/s	224.92 t/s
Googlegoogle-vertex/global	85 t/s	120 t/s	155 t/s	242 t/s
Googlegoogle-vertex/global/priority	82 t/s	110.25 t/s	125.4 t/s	158.66 t/s
Google AI Studiogoogle-ai-studio/flex	152 t/s	168 t/s	180.4 t/s	219 t/s
Google AI Studiogoogle-ai-studio	106 t/s	160 t/s	200 t/s	241 t/s
Google AI Studiogoogle-ai-studio/priority	150 t/s	173.5 t/s	187.6 t/s	196.06 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/euObserved Oct 10, 2026, 11:31 AM UTC

100%

88.79%

Googlegoogle-vertexObserved Oct 10, 2026, 11:31 AM UTC

100%

36.67%

50.07%

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

100%

96.11%

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

100%

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

100%

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

—

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-2.5-flashObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 20

Intelligence

15.5

Design Arena	Category	Elo	Win rate	Rank
models	3d	1,076	47.4%	94
models	codecategories	1,108	46.9%	94
models	dataviz	1,137	49.1%	83
models	gamedev	1,073	44.3%	99
models	uicomponent	1,096	48.9%	91
models	website	1,118	47.1%	96
models	svg	1,019	43.1%	80

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

gpqa diamondGoogle: Gemini 2.5 Flash

72.811%

tau bench verified airlineGoogle: Gemini 2.5 Flash

56.667%

Evaluation	Configuration	Source	Results	Details
models · uicomponent	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,083 Elo	Details
models · codecategories	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,093 Elo	Details
models · website	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	1,066 Elo	Details
models · uicomponent	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	995 Elo	Details
models · codecategories	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	1,049 Elo	Details
models · 3d	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,051 Elo	Details
models · gamedev	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,055 Elo	Details
models · website	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,107 Elo	Details
models · dataviz	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	1,057 Elo	Details
models · svg	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,009 Elo	Details
models · gamedev	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	994 Elo	Details
models · dataviz	Gemini 2.5 Flash Preview 09-2025google/gemini-2.5-flash	Design Arena	1,131 Elo	Details
gpqa diamond	Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash	OpenRouter	72.811%	Details
tau bench verified airline	Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash	OpenRouter	56.667%	Details
models · 3d	Gemini 2.5 Flashgoogle/gemini-2.5-flash	Design Arena	1,001 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 14, 2026.

Apps & session costs

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

30-day sample · through Nov 1, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	google/gemini-2.5-flash	10–49 turns	$0.067628	Details
Hermes Agent	google/gemini-2.5-flash	1 turn	$0.003271	Details
Hermes Agent	google/gemini-2.5-flash	2–9 turns	$0.011064	Details
Hermes Agent	google/gemini-2.5-flash	50+ turns	$0.519484	Details

Source: OpenRouter, as of Nov 9, 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 usage3,903,830,181,606 reported tokens · 59 days with observations

83B0

2026-08-17
64,520,541,435 tokens

2026-08-18
65,741,159,528 tokens

2026-08-19
74,154,138,959 tokens

2026-08-20
72,976,529,136 tokens

2026-08-21
70,733,969,454 tokens

2026-08-22
49,963,383,586 tokens

2026-08-23
47,958,508,458 tokens

2026-08-24
62,188,213,336 tokens

2026-08-25
66,786,904,659 tokens

2026-08-26
68,528,310,681 tokens

2026-08-27
69,866,938,238 tokens

2026-08-28
63,707,727,215 tokens

2026-08-29
49,194,099,157 tokens

2026-08-30
50,437,772,127 tokens

2026-08-31
70,326,631,274 tokens

2026-09-01
82,172,611,702 tokens

2026-09-02
79,966,973,806 tokens

2026-09-03
83,409,412,790 tokens

2026-09-04
74,213,322,893 tokens

2026-09-05
61,213,136,916 tokens

2026-09-06
53,927,197,356 tokens

2026-09-07
62,829,517,133 tokens

2026-09-08
70,195,558,462 tokens

2026-09-09
72,060,992,626 tokens

2026-09-10
74,674,736,012 tokens

2026-09-11
67,141,858,681 tokens

2026-09-12
55,061,837,471 tokens

2026-09-13
50,986,419,937 tokens

2026-09-14
74,518,148,050 tokens

2026-09-15
74,352,816,528 tokens

2026-09-16
81,298,899,143 tokens

2026-09-17
74,560,218,661 tokens

2026-09-18
72,260,125,487 tokens

2026-09-19
56,985,018,648 tokens

2026-09-20
50,742,784,005 tokens

2026-09-21
80,234,123,900 tokens

2026-09-22
81,323,530,248 tokens

2026-09-23
80,082,584,928 tokens

2026-09-24
71,083,786,532 tokens

2026-09-25
71,007,128,407 tokens

2026-09-26
55,497,736,684 tokens

2026-09-27
49,788,692,773 tokens

2026-09-28
66,175,667,564 tokens

2026-09-29
74,086,959,818 tokens

2026-09-30
70,022,255,456 tokens

2026-10-01
71,962,411,813 tokens

2026-10-02
80,556,313,994 tokens

2026-10-03
58,020,919,767 tokens

2026-10-04
56,855,453,625 tokens

2026-10-05
70,767,161,371 tokens

2026-10-06
68,915,973,396 tokens

2026-10-07
65,146,854,660 tokens

2026-10-08
64,145,661,804 tokens

2026-10-09
60,816,761,143 tokens

2026-10-10
51,134,129,884 tokens

2026-10-12
59,496,528,452 tokens

2026-10-13
59,916,006,186 tokens

2026-10-14
60,234,923,689 tokens

2026-10-15
56,902,201,962 tokens

Aug 16, 2026Nov 13, 2026

Daily observations · 59 days

Date (UTC)	Reported tokens	Reported routes
Oct 15, 2026	56,902,201,962	1
Oct 14, 2026	60,234,923,689	1
Oct 13, 2026	59,916,006,186	1
Oct 12, 2026	59,496,528,452	1
Oct 10, 2026	51,134,129,884	1
Oct 9, 2026	60,816,761,143	1
Oct 8, 2026	64,145,661,804	1
Oct 7, 2026	65,146,854,660	1
Oct 6, 2026	68,915,973,396	1
Oct 5, 2026	70,767,161,371	1
Oct 4, 2026	56,855,453,625	1
Oct 3, 2026	58,020,919,767	1
Oct 2, 2026	80,556,313,994	1
Oct 1, 2026	71,962,411,813	1
Sep 30, 2026	70,022,255,456	1
Sep 29, 2026	74,086,959,818	1
Sep 28, 2026	66,175,667,564	1
Sep 27, 2026	49,788,692,773	1
Sep 26, 2026	55,497,736,684	1
Sep 25, 2026	71,007,128,407	1
Sep 24, 2026	71,083,786,532	1
Sep 23, 2026	80,082,584,928	1
Sep 22, 2026	81,323,530,248	1
Sep 21, 2026	80,234,123,900	1
Sep 20, 2026	50,742,784,005	1
Sep 19, 2026	56,985,018,648	1
Sep 18, 2026	72,260,125,487	1
Sep 17, 2026	74,560,218,661	1
Sep 16, 2026	81,298,899,143	1
Sep 15, 2026	74,352,816,528	1
Sep 14, 2026	74,518,148,050	1
Sep 13, 2026	50,986,419,937	1
Sep 12, 2026	55,061,837,471	1
Sep 11, 2026	67,141,858,681	1
Sep 10, 2026	74,674,736,012	1
Sep 9, 2026	72,060,992,626	1
Sep 8, 2026	70,195,558,462	1
Sep 7, 2026	62,829,517,133	1
Sep 6, 2026	53,927,197,356	1
Sep 5, 2026	61,213,136,916	1
Sep 4, 2026	74,213,322,893	1
Sep 3, 2026	83,409,412,790	1
Sep 2, 2026	79,966,973,806	1
Sep 1, 2026	82,172,611,702	1
Aug 31, 2026	70,326,631,274	1
Aug 30, 2026	50,437,772,127	1
Aug 29, 2026	49,194,099,157	1
Aug 28, 2026	63,707,727,215	1
Aug 27, 2026	69,866,938,238	1
Aug 26, 2026	68,528,310,681	1
Aug 25, 2026	66,786,904,659	1
Aug 24, 2026	62,188,213,336	1
Aug 23, 2026	47,958,508,458	1
Aug 22, 2026	49,963,383,586	1
Aug 21, 2026	70,733,969,454	1
Aug 20, 2026	72,976,529,136	1
Aug 19, 2026	74,154,138,959	1
Aug 18, 2026	65,741,159,528	1
Aug 17, 2026	64,520,541,435	1

Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 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-2.5-flashObserved Oct 10, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 65,535
Tokenizer: Gemini
Input: file, image, text, audio, video
Output: text
Moderation: No
Knowledge cutoff: 2025-01-31
Retirement: 2026-10-20
Added to OpenRouter: 2025-06-17

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

Model IDgoogle/gemini-2.5-flash

Version IDgoogle/gemini-2.5-flash

Reasoning

Required: No
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

include_reasoning
max_tokens
reasoning
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 2.5 Flash cost?

Listed rates start at $0.15 per million input tokens and $1.25 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 2.5 Flash?

There are 39 cataloged offers across 32 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 · 74cd60fc549c
Sep 14, 2026 · 56d1c9aa103b
Sep 12, 2026 · 9c129d8a0eb2