Home/Models
Models/Google

Gemini 3 Flash Preview

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.

The model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.

google/gemini-3-flash-preview
Organization
Google
Family
gemini-flash
Providers
19
Context
1,048,576
Output limit
65,536
Knowledge
2025-01
Release
2025-12-17
Updated
2025-12-17
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.

27 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
Abacus
gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
AnyAPI
google/gemini-3-flash-preview
1,048,57665,536— / —YesYesYes
View
CrossModel
gemini/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Databricks
databricks-gemini-3-flash
1,048,57665,536$0.50 / $3.00YesYesYes
View
DevPass (LLM Gateway)
gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Eden AI
vertex/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Eden AI
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Kilo Gateway
google/gemini-3-flash-preview
1,048,57665,536$0.25 / $1.50YesYesYes
View
LLM Gateway
google-vertex/gemini-3-flash-preview
1,048,57665,535$0.50 / $3.00YesYesYes
View
LLM Gateway
google-ai-studio/gemini-3-flash-preview
1,048,57665,535$0.50 / $3.00YesYesYes
View
Merge Gateway
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
NanoGPT
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
NanoGPT
google/gemini-3-flash-preview-thinking
1,048,57665,536$0.50 / $3.00YesNoNo
View
Neon
gemini-3-flash
1,048,57665,536$0.50 / $3.00YesYesYes
View
Ofox
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Googlevia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.50 / $3.00YesYesYes
View
Googlevia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.25 / $1.50YesYesYes
View
Googlevia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.90 / $5.40YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.50 / $3.00YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.25 / $1.50YesYesYes
View
Google AI Studiovia OpenRouter
google/gemini-3-flash-preview
unknown		1,048,57665,536$0.90 / $5.40YesYesYes
View
Opper
gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
OrcaRouter
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Pioneer
gemini-3-flash
1,000,00065,000$0.50 / $3.00YesYesYes
View
Tempr Gateway
google/gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
View
Venice AI
gemini-3-flash-preview
256,00065,536$0.70 / $3.75YesYesYes
View
Vertex
gemini-3-flash-preview
1,048,57665,536$0.50 / $3.00YesYesYes
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$0.25Per 1M input tokens
Output from$1.50Per 1M output tokens
Available offers27Across 19 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
$0.25$1.50
Google AI Studiogoogle-ai-studio/flex
$0.25$1.50
Googlegoogle-vertex/global
$0.50$3.00
Google AI Studiogoogle-ai-studio
$0.50$3.00
Googlegoogle-vertex/global/priority
$0.90$5.40
Google AI Studiogoogle-ai-studio/priority
$0.90$5.40
google/gemini-3-flash-previewObserved
Input
$0.50
Output
$3.00
Cache read
$0.05
Cache write
$0.083333
Additional fees and pricing conditions
audio
$0.000001 / audio token
image
$0.0000005 / image
web search
$0.014 / search
input audio cache
$0.0000001 / audio token
internal reasoning
$0.000003 / reasoning token
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Googlegoogle-vertex/global$0.50$3.00$0.05$0.083333
Googlegoogle-vertex/global/flex$0.25$1.50$0.025$0.041667
Googlegoogle-vertex/global/priority$0.90$5.40$0.09$0.15
Google AI Studiogoogle-ai-studio$0.50$3.00$0.05$0.083333
Google AI Studiogoogle-ai-studio/flex$0.25$1.50$0.025$0.041667
Google AI Studiogoogle-ai-studio/priority$0.90$5.40$0.09$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/global
1,299.5–8,062.29 ms
Googlegoogle-vertex/global/flex
42,691–256,280 ms
Googlegoogle-vertex/global/priority
987–3,828.7 ms
Google AI Studiogoogle-ai-studio
1,296–4,639.17 ms
Google AI Studiogoogle-ai-studio/flex
1,566–12,286.8 ms
Google AI Studiogoogle-ai-studio/priority
890–5,101.04 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/global1,299.5 ms2,314 ms4,031 ms8,062.29 ms
Googlegoogle-vertex/global/flex42,691 ms115,679 ms181,134 ms256,280 ms
Googlegoogle-vertex/global/priority987 ms1,352.5 ms2,577 ms3,828.7 ms
Google AI Studiogoogle-ai-studio1,296 ms1,549 ms1,947.7 ms4,639.17 ms
Google AI Studiogoogle-ai-studio/flex1,566 ms2,599 ms3,805.2 ms12,286.8 ms
Google AI Studiogoogle-ai-studio/priority890 ms1,052 ms1,641.6 ms5,101.04 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Googlegoogle-vertex/global
91–205 t/s
Googlegoogle-vertex/global/flex
11–188.95 t/s
Googlegoogle-vertex/global/priority
85–188.8 t/s
Google AI Studiogoogle-ai-studio
84–213 t/s
Google AI Studiogoogle-ai-studio/flex
102–209 t/s
Google AI Studiogoogle-ai-studio/priority
76.5–224.54 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
Googlegoogle-vertex/global91 t/s129 t/s154 t/s205 t/s
Googlegoogle-vertex/global/flex11 t/s28 t/s49.9 t/s188.95 t/s
Googlegoogle-vertex/global/priority85 t/s119.5 t/s148.6 t/s188.8 t/s
Google AI Studiogoogle-ai-studio84 t/s113 t/s141 t/s213 t/s
Google AI Studiogoogle-ai-studio/flex102 t/s125.25 t/s150 t/s209 t/s
Google AI Studiogoogle-ai-studio/priority76.5 t/s183 t/s199.7 t/s224.54 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
Googlegoogle-vertex/global/flex
Googlegoogle-vertex/global/priority
Google AI Studiogoogle-ai-studio
Google AI Studiogoogle-ai-studio/flex
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-3-flash-previewObserved
Design ArenaCategoryEloWin rateRank
agentsagenticslides1,07339.3%8
agentsagenticslides(python-pptx)1,07539.3%8
agentsandroidnative1,06548.1%33
agentsfullstack1,06147.4%33
agentsgodotgamedev1,16150.6%19
agentsmobileapps1,08746.6%39
agentspython-pptxslides1,03638.3%27
agentswebapps1,10348.5%33
models3d1,19962.7%47
modelscodecategories1,19557.6%53
modelsgamedev1,17958.3%60
modelswebsite1,20357%54

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 Flash Preview
75.333%
gpqa diamondGoogle: Gemini 3 Flash Preview
88.384%
EvaluationConfigurationSourceResultsDetails
models · gamedevGemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217Design Arena1,179 Elo
Details
models · codecategoriesGemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217Design Arena1,195 Elo
Details
tau bench verified airlineGoogle: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217OpenRouter75.333%
Details
models · websiteGemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217Design Arena1,203 Elo
Details
models · 3dGemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217Design Arena1,199 Elo
Details
gpqa diamondGoogle: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217OpenRouter88.384%
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-3-flash-preview-2025121750+ turns
$0.567362
Details
Hermes Agentgoogle/gemini-3-flash-preview-202512172–9 turns
$0.017859
Details
Hermes Agentgoogle/gemini-3-flash-preview-2025121710–49 turns
$0.091582
Details
Hermes Agentgoogle/gemini-3-flash-preview-202512171 turn
$0.001543
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 usage10,995,630,081,231 reported tokens · 89 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 89 days
Date (UTC)Reported tokensReported routes
Oct 3, 2026102,998,997,8141
Oct 2, 2026134,233,419,3691
Oct 1, 2026110,540,795,5141
Sep 30, 2026101,807,735,2461
Sep 29, 2026110,081,450,8771
Sep 28, 2026113,259,970,5631
Sep 27, 202695,625,357,5821
Sep 26, 202692,778,047,9711
Sep 25, 2026120,022,455,7891
Sep 24, 2026118,229,141,0911
Sep 23, 2026122,000,495,2721
Sep 22, 2026120,980,882,9551
Sep 21, 2026119,795,563,7891
Sep 20, 202694,766,834,0601
Sep 19, 202694,331,009,1871
Sep 18, 2026124,082,357,4351
Sep 17, 2026115,324,840,3211
Sep 16, 2026123,215,951,8731
Sep 15, 2026120,316,281,6421
Sep 14, 2026119,116,842,1231
Sep 13, 2026102,389,467,6021
Sep 12, 202698,926,169,2481
Sep 11, 2026112,601,727,0291
Sep 10, 2026132,337,442,7161
Sep 9, 2026122,682,849,4691
Sep 8, 2026115,177,986,7671
Sep 7, 2026120,087,693,3381
Sep 6, 2026114,328,994,0591
Sep 5, 2026110,475,396,6931
Sep 4, 2026123,131,374,6471
Sep 3, 2026130,534,285,8691
Sep 2, 2026130,637,336,6801
Sep 1, 2026138,027,296,0371
Aug 31, 2026122,952,066,3531
Aug 30, 202691,998,554,5841
Aug 29, 202692,814,286,5221
Aug 28, 2026112,364,927,6901
Aug 27, 2026121,982,672,2971
Aug 26, 2026116,327,111,7691
Aug 25, 2026120,453,717,9521
Aug 24, 2026113,565,916,8941
Aug 23, 202693,083,274,3021
Aug 22, 2026101,671,578,4441
Aug 21, 2026130,315,733,7011
Aug 20, 2026122,958,301,6481
Aug 19, 2026147,625,747,8941
Aug 18, 2026145,217,505,7761
Aug 17, 2026119,736,516,7241
Aug 16, 202692,101,813,6221
Aug 15, 202686,779,355,0801
Aug 14, 2026116,501,378,6971
Aug 13, 2026129,890,946,1601
Aug 12, 2026130,397,685,7451
Aug 11, 2026139,025,462,0001
Aug 10, 2026144,196,262,7881
Aug 9, 2026102,861,565,5911
Aug 8, 202699,786,780,7511
Aug 7, 2026131,156,385,0021
Aug 6, 2026137,319,037,6101
Aug 5, 2026140,287,163,2681
Aug 4, 2026142,529,117,6311
Aug 3, 2026145,016,143,7561
Aug 2, 2026106,704,694,5011
Aug 1, 2026108,988,250,3731
Jul 31, 2026147,835,344,1141
Jul 30, 2026154,716,892,2291
Jul 29, 2026157,657,761,2461
Jul 28, 2026155,158,120,2131
Jul 27, 2026151,826,365,7821
Jul 26, 2026108,482,012,6781
Jul 25, 2026106,308,668,6541
Jul 24, 2026146,622,624,2951
Jul 23, 2026151,459,127,2821
Jul 22, 2026157,386,132,8411
Jul 21, 2026155,156,840,6361
Jul 20, 2026149,476,095,8211
Jul 19, 2026107,447,033,2151
Jul 18, 2026108,744,596,5081
Jul 17, 2026141,759,540,3611
Jul 16, 2026144,966,265,9151
Jul 15, 2026154,967,917,9411
Jul 14, 2026150,754,104,8921
Jul 13, 2026145,211,394,4051
Jul 12, 2026101,450,784,6791
Jul 11, 2026107,325,717,8561
Jul 10, 2026142,419,538,5861
Jul 9, 2026142,758,351,4451
Jul 8, 2026142,138,593,7511
Jul 7, 2026152,143,850,1341

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-flash-previewObserved
Context
1,048,576
Maximum output
65,536
Tokenizer
Gemini
Input
text, image, file, audio, video
Output
text
Moderation
No
Added to OpenRouter
2025-12-17
Base URLhttps://openrouter.ai/api/v1
Model IDgoogle/gemini-3-flash-preview
Version IDgoogle/gemini-3-flash-preview-20251217

Reasoning

Required
No
Enabled by default
Not reported
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 Flash Preview cost?

Listed rates start at $0.25 per million input tokens and $1.50 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 3 Flash Preview?

There are 27 cataloged offers across 19 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.

  • · 6fa4ae8ac1ac
  • · c00fef7d4971