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.
- Organization
- Family
- gemini-flash
- Providers
- 30
- Context
- 1,048,576
- Output limit
- 65,536
- Knowledge
- 2025-01
- Release
- 2025-12-17
- 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.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| 302.AI | gemini-3-flash-preview | 1,000,000 | 65,536 | — / — | — | — | — | View |
| Abacus | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| AIHubMix | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| AnyAPI | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Cloudflare AI Gateway | google/gemini-3-flash | 1,000,000 | 65,536 | — / — | — | — | — | View |
| CrossModel | gemini/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Databricks | databricks-gemini-3-flash | 1,048,576 | 65,536 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Eden AI | vertex/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Eden AI | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| FrogBot | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Jiekou.AI | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Kilo Gateway | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| LLM Gateway | google-vertex/gemini-3-flash-preview | 1,048,576 | 65,535 | — / — | — | — | — | View |
| LLM Gateway | google-ai-studio/gemini-3-flash-preview | 1,048,576 | 65,535 | — / — | — | — | — | View |
| Merge Gateway | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| NanoGPT | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| NanoGPT | google/gemini-3-flash-preview-thinking | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Neon | gemini-3-flash | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Ofox | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| OpenCode | gemini-3-flash | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Googlevia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.50 / $3.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.25 / $1.50 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.90 / $5.40 | Yes | Yes | Yes | View |
| Google AI Studiovia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.50 / $3.00 | Yes | Yes | Yes | View |
| Google AI Studiovia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.25 / $1.50 | Yes | Yes | Yes | View |
| Google AI Studiovia OpenRouter | google/gemini-3-flash-preview unknown | 1,048,576 | 65,536 | $0.90 / $5.40 | Yes | Yes | Yes | View |
| Opper | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| OrcaRouter | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Perplexity Agent | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Poe | google/gemini-3-flash | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Prime Inference | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| QiHang | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Qiniu | gemini-3.0-flash-preview | 1,000,000 | 64,000 | — / — | — | — | — | View |
| Tempr Gateway | google/gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| Venice AI | gemini-3-flash-preview | 256,000 | 65,536 | — / — | — | — | — | View |
| Vertex | gemini-3-flash-preview | 1,048,576 | 65,536 | — / — | — | — | — | View |
| ZenMux | google/gemini-3-flash-preview | 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.
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.
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
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache 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.
Time to first token · milliseconds
All latency percentiles 6 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Googlegoogle-vertex/global | 1,269 ms | 2,006.25 ms | 3,664.8 ms | 8,638.36 ms |
| Googlegoogle-vertex/global/flex | 18,699 ms | 64,523 ms | 126,049.2 ms | 275,161.18 ms |
| Googlegoogle-vertex/global/priority | 1,051.5 ms | 1,802.5 ms | 2,990.7 ms | 45,745.66 ms |
| Google AI Studiogoogle-ai-studio | 1,330 ms | 1,660.25 ms | 2,322.8 ms | 11,321.14 ms |
| Google AI Studiogoogle-ai-studio/flex | 1,367 ms | 3,564 ms | 5,389.5 ms | 12,602.05 ms |
| Google AI Studiogoogle-ai-studio/priority | 925 ms | 1,158.5 ms | 1,634.6 ms | 7,455.9 ms |
Output throughput · tokens per second
All throughput percentiles 6 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Googlegoogle-vertex/global | 83 t/s | 122 t/s | 156 t/s | 202 t/s |
| Googlegoogle-vertex/global/flex | 6 t/s | 21 t/s | 67.2 t/s | 149.26 t/s |
| Googlegoogle-vertex/global/priority | 73 t/s | 111 t/s | 151.2 t/s | 185.88 t/s |
| Google AI Studiogoogle-ai-studio | 89 t/s | 118 t/s | 151.9 t/s | 247 t/s |
| Google AI Studiogoogle-ai-studio/flex | 93 t/s | 116 t/s | 133 t/s | 225 t/s |
| Google AI Studiogoogle-ai-studio/priority | 106 t/s | 117 t/s | 129 t/s | 207.44 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.
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.
google/gemini-3-flash-previewObserved | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| agents | agenticslides | 1,073 | 39.3% | 8 |
| agents | agenticslides(python-pptx) | 1,075 | 39.3% | 8 |
| agents | androidnative | 1,065 | 48.1% | 33 |
| agents | fullstack | 1,063 | 47.4% | 33 |
| agents | godotgamedev | 1,161 | 50.6% | 19 |
| agents | mobileapps | 1,087 | 46.6% | 39 |
| agents | python-pptxslides | 1,036 | 38.3% | 27 |
| agents | webapps | 1,103 | 48.5% | 34 |
| models | 3d | 1,189 | 62.7% | 50 |
| models | codecategories | 1,193 | 57.6% | 55 |
| models | gamedev | 1,173 | 58.3% | 63 |
| models | website | 1,201 | 57% | 57 |
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| gpqa diamond | Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | OpenRouter | 88.468% | Details |
| tau bench verified airline | Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | OpenRouter | 73.333% | Details |
| models · gamedev | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | Design Arena | 1,156 Elo | Details |
| models · website | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | Design Arena | 1,188 Elo | Details |
| models · 3d | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | Design Arena | 1,163 Elo | Details |
| models · codecategories | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-20251217 | Design Arena | 1,179 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.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Hermes Agent | google/gemini-3-flash-preview-20251217 | 1 turn | $0.001913 | Details |
| Hermes Agent | google/gemini-3-flash-preview-20251217 | 50+ turns | $0.477921 | Details |
| Hermes Agent | google/gemini-3-flash-preview-20251217 | 10–49 turns | $0.078319 | Details |
| Hermes Agent | google/gemini-3-flash-preview-20251217 | 2–9 turns | $0.015433 | 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.
92,101,813,622 tokens
119,736,516,724 tokens
145,217,505,776 tokens
147,625,747,894 tokens
122,958,301,648 tokens
130,315,733,701 tokens
101,671,578,444 tokens
93,083,274,302 tokens
113,565,916,894 tokens
120,453,717,952 tokens
116,327,111,769 tokens
121,982,672,297 tokens
112,364,927,690 tokens
92,814,286,522 tokens
91,998,554,584 tokens
122,952,066,353 tokens
138,027,296,037 tokens
130,637,336,680 tokens
130,534,285,869 tokens
123,131,374,647 tokens
110,475,396,693 tokens
114,328,994,059 tokens
120,087,693,338 tokens
115,177,986,767 tokens
122,682,849,469 tokens
132,337,442,716 tokens
112,601,727,029 tokens
98,926,169,248 tokens
102,389,467,602 tokens
119,116,842,123 tokens
120,316,281,642 tokens
123,215,951,873 tokens
115,324,840,321 tokens
124,082,357,435 tokens
94,331,009,187 tokens
94,766,834,060 tokens
119,795,563,789 tokens
120,980,882,955 tokens
122,000,495,272 tokens
118,229,141,091 tokens
120,022,455,789 tokens
92,778,047,971 tokens
95,625,357,582 tokens
113,259,970,563 tokens
110,081,450,877 tokens
101,807,735,246 tokens
110,540,795,514 tokens
134,233,419,369 tokens
102,998,997,814 tokens
90,627,214,746 tokens
99,788,077,150 tokens
126,705,356,194 tokens
118,230,712,715 tokens
139,217,420,111 tokens
186,658,045,090 tokens
174,178,832,228 tokens
129,088,806,192 tokens
190,675,611,819 tokens
156,707,604,677 tokens
126,276,810,325 tokens
112,541,885,553 tokens
97,900,539,817 tokens
85,180,307,394 tokens
100,686,439,660 tokens
113,430,747,130 tokens
97,237,150,147 tokens
111,339,555,839 tokens
100,976,721,285 tokens
97,128,402,862 tokens
96,213,623,469 tokens
89,686,769,367 tokens
96,956,981,880 tokens
93,904,158,551 tokens
93,404,053,519 tokens
86,190,513,995 tokens
82,725,763,507 tokens
79,026,376,905 tokens
88,085,626,365 tokens
91,089,582,145 tokens
91,635,692,737 tokens
92,754,438,325 tokens
90,776,183,395 tokens
82,409,230,819 tokens
79,999,570,548 tokens
75,641,818,036 tokens
94,464,876,841 tokens
94,374,148,222 tokens
95,461,787,550 tokens
99,070,090,103 tokens
99,548,438,989 tokens
Daily observations · 90 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Nov 13, 2026 | 99,548,438,989 | 1 |
| Nov 12, 2026 | 99,070,090,103 | 1 |
| Nov 11, 2026 | 95,461,787,550 | 1 |
| Nov 10, 2026 | 94,374,148,222 | 1 |
| Nov 9, 2026 | 94,464,876,841 | 1 |
| Nov 8, 2026 | 75,641,818,036 | 1 |
| Nov 7, 2026 | 79,999,570,548 | 1 |
| Nov 6, 2026 | 82,409,230,819 | 1 |
| Nov 5, 2026 | 90,776,183,395 | 1 |
| Nov 4, 2026 | 92,754,438,325 | 1 |
| Nov 3, 2026 | 91,635,692,737 | 1 |
| Nov 2, 2026 | 91,089,582,145 | 1 |
| Nov 1, 2026 | 88,085,626,365 | 1 |
| Oct 31, 2026 | 79,026,376,905 | 1 |
| Oct 30, 2026 | 82,725,763,507 | 1 |
| Oct 29, 2026 | 86,190,513,995 | 1 |
| Oct 28, 2026 | 93,404,053,519 | 1 |
| Oct 27, 2026 | 93,904,158,551 | 1 |
| Oct 26, 2026 | 96,956,981,880 | 1 |
| Oct 25, 2026 | 89,686,769,367 | 1 |
| Oct 24, 2026 | 96,213,623,469 | 1 |
| Oct 23, 2026 | 97,128,402,862 | 1 |
| Oct 22, 2026 | 100,976,721,285 | 1 |
| Oct 21, 2026 | 111,339,555,839 | 1 |
| Oct 20, 2026 | 97,237,150,147 | 1 |
| Oct 19, 2026 | 113,430,747,130 | 1 |
| Oct 18, 2026 | 100,686,439,660 | 1 |
| Oct 17, 2026 | 85,180,307,394 | 1 |
| Oct 16, 2026 | 97,900,539,817 | 1 |
| Oct 15, 2026 | 112,541,885,553 | 1 |
| Oct 14, 2026 | 126,276,810,325 | 1 |
| Oct 13, 2026 | 156,707,604,677 | 1 |
| Oct 12, 2026 | 190,675,611,819 | 1 |
| Oct 11, 2026 | 129,088,806,192 | 1 |
| Oct 10, 2026 | 174,178,832,228 | 1 |
| Oct 9, 2026 | 186,658,045,090 | 1 |
| Oct 8, 2026 | 139,217,420,111 | 1 |
| Oct 7, 2026 | 118,230,712,715 | 1 |
| Oct 6, 2026 | 126,705,356,194 | 1 |
| Oct 5, 2026 | 99,788,077,150 | 1 |
| Oct 4, 2026 | 90,627,214,746 | 1 |
| Oct 3, 2026 | 102,998,997,814 | 1 |
| Oct 2, 2026 | 134,233,419,369 | 1 |
| Oct 1, 2026 | 110,540,795,514 | 1 |
| Sep 30, 2026 | 101,807,735,246 | 1 |
| Sep 29, 2026 | 110,081,450,877 | 1 |
| Sep 28, 2026 | 113,259,970,563 | 1 |
| Sep 27, 2026 | 95,625,357,582 | 1 |
| Sep 26, 2026 | 92,778,047,971 | 1 |
| Sep 25, 2026 | 120,022,455,789 | 1 |
| Sep 24, 2026 | 118,229,141,091 | 1 |
| Sep 23, 2026 | 122,000,495,272 | 1 |
| Sep 22, 2026 | 120,980,882,955 | 1 |
| Sep 21, 2026 | 119,795,563,789 | 1 |
| Sep 20, 2026 | 94,766,834,060 | 1 |
| Sep 19, 2026 | 94,331,009,187 | 1 |
| Sep 18, 2026 | 124,082,357,435 | 1 |
| Sep 17, 2026 | 115,324,840,321 | 1 |
| Sep 16, 2026 | 123,215,951,873 | 1 |
| Sep 15, 2026 | 120,316,281,642 | 1 |
| Sep 14, 2026 | 119,116,842,123 | 1 |
| Sep 13, 2026 | 102,389,467,602 | 1 |
| Sep 12, 2026 | 98,926,169,248 | 1 |
| Sep 11, 2026 | 112,601,727,029 | 1 |
| Sep 10, 2026 | 132,337,442,716 | 1 |
| Sep 9, 2026 | 122,682,849,469 | 1 |
| Sep 8, 2026 | 115,177,986,767 | 1 |
| Sep 7, 2026 | 120,087,693,338 | 1 |
| Sep 6, 2026 | 114,328,994,059 | 1 |
| Sep 5, 2026 | 110,475,396,693 | 1 |
| Sep 4, 2026 | 123,131,374,647 | 1 |
| Sep 3, 2026 | 130,534,285,869 | 1 |
| Sep 2, 2026 | 130,637,336,680 | 1 |
| Sep 1, 2026 | 138,027,296,037 | 1 |
| Aug 31, 2026 | 122,952,066,353 | 1 |
| Aug 30, 2026 | 91,998,554,584 | 1 |
| Aug 29, 2026 | 92,814,286,522 | 1 |
| Aug 28, 2026 | 112,364,927,690 | 1 |
| Aug 27, 2026 | 121,982,672,297 | 1 |
| Aug 26, 2026 | 116,327,111,769 | 1 |
| Aug 25, 2026 | 120,453,717,952 | 1 |
| Aug 24, 2026 | 113,565,916,894 | 1 |
| Aug 23, 2026 | 93,083,274,302 | 1 |
| Aug 22, 2026 | 101,671,578,444 | 1 |
| Aug 21, 2026 | 130,315,733,701 | 1 |
| Aug 20, 2026 | 122,958,301,648 | 1 |
| Aug 19, 2026 | 147,625,747,894 | 1 |
| Aug 18, 2026 | 145,217,505,776 | 1 |
| Aug 17, 2026 | 119,736,516,724 | 1 |
| Aug 16, 2026 | 92,101,813,622 | 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.
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
https://openrouter.ai/api/v1google/gemini-3-flash-previewgoogle/gemini-3-flash-preview-20251217Reasoning
- Required
- No
- Enabled by default
- Not reported
- Default effort
- medium
- Supported efforts
- high, medium, low, minimal
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_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 38 cataloged offers across 30 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.
- ·
67fd40261d3f - ·
6fa4ae8ac1ac - ·
c00fef7d4971