Home/Models
Models/Google

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
22
Context
1,048,576
Output limit
65,536
Knowledge
2025-01
Release
2025-06-17
Updated
2025-06-17
Weights
Closed
Input
text, image, audio, video, 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.

29 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
Abacus
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
AnyAPI
google/gemini-2.5-flash
1,048,57665,536— / —YesYesYes
View
Auriko
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Cortecs
gemini-2.5-flash
1,048,57665,535$0.299 / $2.491YesYesYes
View
CrossModel
gemini/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Databricks
databricks-gemini-2-5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
DevPass (LLM Gateway)
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Google
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Impossibl
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Kenari
gemini-2-5-flash
1,048,57665,536$0.00 / $0.00YesYesYes
View
Kilo Gateway
google/gemini-2.5-flash
1,048,57665,535$0.30 / $2.50YesYesYes
View
LLM Gateway
google-vertex/gemini-2.5-flash
1,048,57665,535$0.30 / $2.50YesYesYes
View
LLM Gateway
google-ai-studio/gemini-2.5-flash
1,048,57665,535$0.30 / $2.50YesYesYes
View
Merge Gateway
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Modelis
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
NanoGPT
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesNo
View
NEAR AI Cloud
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Ofox
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.30 / $2.50YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.30 / $2.50YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.30 / $2.50YesYesYes
View
Googlevia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.54 / $4.50YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.15 / $1.25YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.30 / $2.50YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-2.5-flash
unknown		1,048,57665,535$0.54 / $4.50YesYesYes
View
OrcaRouter
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Requesty
gemini-2.5-flash@eu
1,048,57665,535$0.30 / $2.50YesYesYes
View
SAP AI Core
gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
View
Vercel AI Gateway
google/gemini-2.5-flash
1,048,57665,536$0.30 / $2.50YesYesYes
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 offers29Across 22 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
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
EndpointInput / 1MOutput / 1MCache read / 1MCache 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
829–3,100.34 ms
Googlegoogle-vertex
1,061–2,956.63 ms
Googlegoogle-vertex/global
791–3,763.44 ms
Googlegoogle-vertex/global/priority
485.5–4,427.5 ms
Google AI Studiogoogle-ai-studio/flex
555–2,255.9 ms
Google AI Studiogoogle-ai-studio
613.5–4,886.8 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/eu829 ms1,027 ms1,514.9 ms3,100.34 ms
Googlegoogle-vertex1,061 ms1,235 ms1,431 ms2,956.63 ms
Googlegoogle-vertex/global791 ms1,171 ms1,592.9 ms3,763.44 ms
Googlegoogle-vertex/global/priority485.5 ms801.25 ms1,166.5 ms4,427.5 ms
Google AI Studiogoogle-ai-studio/flex555 ms1,440.5 ms1,612 ms2,255.9 ms
Google AI Studiogoogle-ai-studio613.5 ms1,002 ms1,795 ms4,886.8 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Googlegoogle-vertex/eu
119–242 t/s
Googlegoogle-vertex
59–178 t/s
Googlegoogle-vertex/global
64–228 t/s
Googlegoogle-vertex/global/priority
99–170.72 t/s
Google AI Studiogoogle-ai-studio/flex
147–226.41 t/s
Google AI Studiogoogle-ai-studio
86–226.14 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/eu119 t/s141 t/s163 t/s242 t/s
Googlegoogle-vertex59 t/s68 t/s82 t/s178 t/s
Googlegoogle-vertex/global64 t/s89 t/s128 t/s228 t/s
Googlegoogle-vertex/global/priority99 t/s143.5 t/s155.6 t/s170.72 t/s
Google AI Studiogoogle-ai-studio/flex147 t/s165 t/s184 t/s226.41 t/s
Google AI Studiogoogle-ai-studio86 t/s127 t/s165 t/s226.14 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/eu
Googlegoogle-vertex
Googlegoogle-vertex/global
Googlegoogle-vertex/global/priority
Google AI Studiogoogle-ai-studio/flex
Google AI Studiogoogle-ai-studio
Google AI Studiogoogle-ai-studio/priority

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
Design ArenaCategoryEloWin rateRank
models3d1,08647.4%91
modelscodecategories1,11046.9%92
modelsdataviz1,14249.1%80
modelsgamedev1,07844.3%96
modelsuicomponent1,10048.9%90
modelswebsite1,12247.1%93
modelssvg1,01943.1%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
tau bench verified airlineGoogle: Gemini 2.5 Flash
57.111%
gpqa diamondGoogle: Gemini 2.5 Flash
72.615%
EvaluationConfigurationSourceResultsDetails
models · datavizGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,068 Elo
Details
models · uicomponentGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,100 Elo
Details
models · websiteGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,081 Elo
Details
tau bench verified airlineGoogle: Gemini 2.5 Flashgoogle/gemini-2.5-flashOpenRouter57.111%
Details
models · uicomponentGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,012 Elo
Details
models · 3dGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,086 Elo
Details
models · datavizGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,142 Elo
Details
models · gamedevGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,078 Elo
Details
models · codecategoriesGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,065 Elo
Details
models · gamedevGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,018 Elo
Details
models · codecategoriesGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,110 Elo
Details
gpqa diamondGoogle: Gemini 2.5 Flashgoogle/gemini-2.5-flashOpenRouter72.615%
Details
models · 3dGemini 2.5 Flashgoogle/gemini-2.5-flashDesign Arena1,036 Elo
Details
models · websiteGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,122 Elo
Details
models · svgGemini 2.5 Flash Preview 09-2025google/gemini-2.5-flashDesign Arena1,019 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
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentgoogle/gemini-2.5-flash1 turn
$0.003353
Details
Hermes Agentgoogle/gemini-2.5-flash10–49 turns
$0.070904
Details
Hermes Agentgoogle/gemini-2.5-flash50+ turns
$0.489634
Details
Hermes Agentgoogle/gemini-2.5-flash2–9 turns
$0.011583
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 usage6,514,504,745,067 reported tokens · 89 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 89 days
Date (UTC)Reported tokensReported routes
Oct 3, 202658,020,919,7671
Oct 2, 202680,556,313,9941
Oct 1, 202671,962,411,8131
Sep 30, 202670,022,255,4561
Sep 29, 202674,086,959,8181
Sep 28, 202666,175,667,5641
Sep 27, 202649,788,692,7731
Sep 26, 202655,497,736,6841
Sep 25, 202671,007,128,4071
Sep 24, 202671,083,786,5321
Sep 23, 202680,082,584,9281
Sep 22, 202681,323,530,2481
Sep 21, 202680,234,123,9001
Sep 20, 202650,742,784,0051
Sep 19, 202656,985,018,6481
Sep 18, 202672,260,125,4871
Sep 17, 202674,560,218,6611
Sep 16, 202681,298,899,1431
Sep 15, 202674,352,816,5281
Sep 14, 202674,518,148,0501
Sep 13, 202650,986,419,9371
Sep 12, 202655,061,837,4711
Sep 11, 202667,141,858,6811
Sep 10, 202674,674,736,0121
Sep 9, 202672,060,992,6261
Sep 8, 202670,195,558,4621
Sep 7, 202662,829,517,1331
Sep 6, 202653,927,197,3561
Sep 5, 202661,213,136,9161
Sep 4, 202674,213,322,8931
Sep 3, 202683,409,412,7901
Sep 2, 202679,966,973,8061
Sep 1, 202682,172,611,7021
Aug 31, 202670,326,631,2741
Aug 30, 202650,437,772,1271
Aug 29, 202649,194,099,1571
Aug 28, 202663,707,727,2151
Aug 27, 202669,866,938,2381
Aug 26, 202668,528,310,6811
Aug 25, 202666,786,904,6591
Aug 24, 202662,188,213,3361
Aug 23, 202647,958,508,4581
Aug 22, 202649,963,383,5861
Aug 21, 202670,733,969,4541
Aug 20, 202672,976,529,1361
Aug 19, 202674,154,138,9591
Aug 18, 202665,741,159,5281
Aug 17, 202664,520,541,4351
Aug 16, 202648,669,387,4721
Aug 15, 202650,767,244,2841
Aug 14, 202666,246,058,0621
Aug 13, 202671,803,143,7801
Aug 12, 202670,431,081,9931
Aug 11, 202676,064,973,9701
Aug 10, 202680,826,697,3481
Aug 9, 202662,239,649,0941
Aug 8, 202660,625,866,4391
Aug 7, 202677,576,616,3471
Aug 6, 202673,039,967,0471
Aug 5, 202679,836,336,5481
Aug 4, 202685,427,245,1891
Aug 3, 202680,256,791,5251
Aug 2, 202659,820,970,1551
Aug 1, 202672,285,145,4981
Jul 31, 202681,100,731,3061
Jul 30, 202682,698,783,4881
Jul 29, 202682,153,075,8981
Jul 28, 202685,073,131,1021
Jul 27, 202688,175,503,4311
Jul 26, 202676,725,885,7311
Jul 25, 202678,774,297,7771
Jul 24, 2026102,370,198,1001
Jul 23, 2026101,854,411,1341
Jul 22, 202693,928,991,7971
Jul 21, 202688,458,729,7001
Jul 20, 202685,522,824,5371
Jul 19, 202664,343,769,4921
Jul 18, 202670,540,176,2651
Jul 17, 202697,807,047,7101
Jul 16, 202695,486,921,4071
Jul 15, 202689,272,239,8021
Jul 14, 202690,438,090,2361
Jul 13, 202690,096,760,4271
Jul 12, 202665,197,667,9071
Jul 11, 202687,037,276,5941
Jul 10, 202690,702,965,4361
Jul 9, 202690,875,160,9391
Jul 8, 202697,084,360,9461
Jul 7, 202693,370,043,7201

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-2.5-flashObserved
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 $0.00 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 2.5 Flash?

There are 29 cataloged offers across 22 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.

  • · 56d1c9aa103b
  • · 9c129d8a0eb2