Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

google/gemini-3.8-flash

Organization: Google
Family: gemini-flash
Providers: 22
Context: 1,048,576
Output limit: 65,536
Knowledge: —
Release: 2026-09-02
Updated: 2026-09-02
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.

33 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
AIHubMix	gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Cortecs	gemini-3.8-flash	1,048,576	65,535	$0.825 / $4.125	Yes	Yes	Yes	View
CrossModel	gemini/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-flash-latest	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	google/gemini-flash-latest	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.8-flash@us	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	vertex/gemini-3.8-flash@eu	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Eden AI	google/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
GitHub Copilot	gemini-3.8-flash	1,000,000	64,000	$0.75 / $3.75	Yes	Yes	Yes	View
Google	gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Kilo Gateway	google/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
LLM Gateway	google-ai-studio/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Merge Gateway	google/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
NanoGPT	google/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Ofox	google/gemini-3.8-flash	1,000,000	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
OpenCode Zen	gemini-3.8-flash	1,048,576	65,536	$1.50 / $7.50	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$1.35 / $6.75	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$0.375 / $1.875	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.8-flash unknown	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Opper	gemini-3.8-flash	1,048,576	65,536	$0.825 / $4.125	Yes	Yes	Yes	View
Requesty	gemini-3.8-flash@eu	1,048,576	65,535	$0.825 / $4.125	Yes	Yes	Yes	View
Requesty	gemini-3.8-flash	1,048,576	65,535	$0.75 / $3.75	Yes	Yes	Yes	View
SAP AI Core	gemini-3.8-flash	1,048,576	65,536	— / —	Yes	Yes	Yes	View
Tempr Gateway	google/gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Venice AI	gemini-3-8-flash	1,000,000	65,536	$0.9375 / $4.6875	Yes	Yes	Yes	View
Vercel AI Gateway	google/gemini-3.8-flash	1,000,000	65,535	$0.75 / $3.75	Yes	Yes	Yes	View
Vertex	gemini-3.8-flash	1,048,576	65,536	$0.75 / $3.75	Yes	Yes	Yes	View
Vivgrid	gemini-3.8-flash	1,048,576	128,000	$0.75 / $3.75	Yes	Yes	Yes	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 offers33Across 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 · 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-3.8-flashObserved Oct 4, 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	$0.75	$3.75	$0.075	$0.041667
Googlegoogle-vertex/global/priority	$1.35	$6.75	$0.135	$0.075
Googlegoogle-vertex/global/flex	$0.375	$1.875	$0.0375	$0.020833
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
Google AI Studiogoogle-ai-studio	$0.75	$3.75	$0.075	$0.041667

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

2,186–15,248.09 ms

Googlegoogle-vertex/global/priority

2,143–12,593.88 ms

Googlegoogle-vertex/global/flex

11,851–189,803.98 ms

Google AI Studiogoogle-ai-studio/priority

2,558–5,690.16 ms

Google AI Studiogoogle-ai-studio/flex

1,739–7,862.09 ms

Google AI Studiogoogle-ai-studio

1,472–7,382.98 ms

All latency percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	2,186 ms	3,102.25 ms	4,970.3 ms	15,248.09 ms
Googlegoogle-vertex/global/priority	2,143 ms	3,114 ms	4,193.8 ms	12,593.88 ms
Googlegoogle-vertex/global/flex	11,851 ms	12,355.75 ms	15,190.6 ms	189,803.98 ms
Google AI Studiogoogle-ai-studio/priority	2,558 ms	3,026 ms	3,571.4 ms	5,690.16 ms
Google AI Studiogoogle-ai-studio/flex	1,739 ms	2,151 ms	2,702 ms	7,862.09 ms
Google AI Studiogoogle-ai-studio	1,472 ms	1,947 ms	2,728.9 ms	7,382.98 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Googlegoogle-vertex/global

94–192 t/s

Googlegoogle-vertex/global/priority

88–195.12 t/s

Googlegoogle-vertex/global/flex

9–121.05 t/s

Google AI Studiogoogle-ai-studio/priority

196–299.1 t/s

Google AI Studiogoogle-ai-studio/flex

166–393 t/s

Google AI Studiogoogle-ai-studio

149–356.09 t/s

All throughput percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	94 t/s	125 t/s	152 t/s	192 t/s
Googlegoogle-vertex/global/priority	88 t/s	120 t/s	158 t/s	195.12 t/s
Googlegoogle-vertex/global/flex	9 t/s	11 t/s	14 t/s	121.05 t/s
Google AI Studiogoogle-ai-studio/priority	196 t/s	215 t/s	232 t/s	299.1 t/s
Google AI Studiogoogle-ai-studio/flex	166 t/s	254 t/s	357 t/s	393 t/s
Google AI Studiogoogle-ai-studio	149 t/s	216 t/s	282 t/s	356.09 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/globalObserved Oct 4, 2026, 11:31 AM UTC

98.49%

98.97%

99.51%

Googlegoogle-vertex/global/priorityObserved Oct 4, 2026, 11:31 AM UTC

—

100%

99.5%

Googlegoogle-vertex/global/flexObserved Oct 4, 2026, 11:31 AM UTC

—

99.97%

99.73%

Google AI Studiogoogle-ai-studio/priorityObserved Oct 4, 2026, 11:31 AM UTC

100%

99.81%

Google AI Studiogoogle-ai-studio/flexObserved Oct 4, 2026, 11:31 AM UTC

100%

99.98%

Google AI Studiogoogle-ai-studioObserved Oct 4, 2026, 11:31 AM UTC

100%

99.91%

99.93%

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-3.8-flashObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 80

Coding

76.3

Agentic

40.2

Intelligence

40.9

Design Arena	Category	Elo	Win rate	Rank
agents	androidnative	1,077	33.2%	31
agents	fullstack	1,242	48.1%	11
agents	godotgamedev	1,273	53%	5
agents	mobileapps	1,231	54.2%	8
agents	python-pptxslides	1,178	39.8%	19
agents	webapps	1,230	46.1%	11
models	3d	1,310	50.4%	14
models	asciiart	1,285	53.8%	9
models	codecategories	1,310	50.8%	11
models	dataviz	1,267	49.9%	25
models	gamedev	1,321	51.6%	10
models	svg	1,287	53.4%	11
models	uicomponent	1,321	53.4%	12
models	website	1,308	50.5%	10

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 3.8 Flash

95.637%

tau bench verified airlineGoogle: Gemini 3.8 Flash

71.277%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Google: Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	OpenRouter	95.637%	Details
models · svg	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,287 Elo	Details
Composite indices	Gemini 3.8 Flash (high)google/gemini-3.8-flash-20260902	Artificial Analysis	Intelligence 40.9 · Coding 76.3 · Agentic 40.2	Details
models · gamedev	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,321 Elo	Details
models · codecategories	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,310 Elo	Details
models · website	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,308 Elo	Details
models · uicomponent	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,321 Elo	Details
tau bench verified airline	Google: Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	OpenRouter	71.277%	Details
models · dataviz	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,267 Elo	Details
models · asciiart	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,285 Elo	Details
models · 3d	Gemini 3.8 Flashgoogle/gemini-3.8-flash-20260902	Design Arena	1,310 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

Application	Model route	Turns	Median cost / session	Details
Codex	google/gemini-3.8-flash-20260902	10–49 turns	$0.286436	Details
Hermes Agent	google/gemini-3.8-flash-20260902	1 turn	$0.006797	Details
Claude Code	google/gemini-3.8-flash-20260902	1 turn	$0.003451	Details
Kilo Code	google/gemini-3.8-flash-20260902	50+ turns	$1.569869	Details
Hermes Agent	google/gemini-3.8-flash-20260902	50+ turns	$1.296302	Details
Kilo Code	google/gemini-3.8-flash-20260902	10–49 turns	$0.286308	Details
Codex	google/gemini-3.8-flash-20260902	2–9 turns	$0.041508	Details
Kilo Code	google/gemini-3.8-flash-20260902	1 turn	$0.000688	Details
Hermes Agent	google/gemini-3.8-flash-20260902	2–9 turns	$0.028855	Details
Codex	google/gemini-3.8-flash-20260902	1 turn	$0.009346	Details
Hermes Agent	google/gemini-3.8-flash-20260902	10–49 turns	$0.207746	Details
Kilo Code	google/gemini-3.8-flash-20260902	2–9 turns	$0.037861	Details
Claude Code	google/gemini-3.8-flash-20260902	50+ turns	$3.022561	Details
Claude Code	google/gemini-3.8-flash-20260902	2–9 turns	$0.018871	Details
Codex	google/gemini-3.8-flash-20260902	50+ turns	$1.501692	Details
Claude Code	google/gemini-3.8-flash-20260902	10–49 turns	$0.31025	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 usage9,904,214,959,147 reported tokens · 32 days with observations

653B0

2026-09-02
55,220,179,915 tokens

2026-09-03
273,211,217,398 tokens

2026-09-04
317,550,771,802 tokens

2026-09-05
216,064,543,480 tokens

2026-09-06
205,638,900,246 tokens

2026-09-07
276,502,500,205 tokens

2026-09-08
565,738,446,714 tokens

2026-09-09
652,963,426,227 tokens

2026-09-10
363,587,380,793 tokens

2026-09-11
268,990,059,254 tokens

2026-09-12
227,647,146,646 tokens

2026-09-13
200,168,978,092 tokens

2026-09-14
298,868,541,030 tokens

2026-09-15
414,576,677,239 tokens

2026-09-16
389,353,011,138 tokens

2026-09-17
327,315,493,226 tokens

2026-09-18
271,983,234,276 tokens

2026-09-19
237,332,736,721 tokens

2026-09-20
254,730,762,105 tokens

2026-09-21
345,986,100,251 tokens

2026-09-22
391,040,911,838 tokens

2026-09-23
310,334,451,604 tokens

2026-09-24
312,983,002,538 tokens

2026-09-25
340,315,765,567 tokens

2026-09-26
231,789,605,233 tokens

2026-09-27
224,013,060,669 tokens

2026-09-28
302,500,473,863 tokens

2026-09-29
330,481,407,986 tokens

2026-09-30
365,689,306,932 tokens

2026-10-01
337,946,027,237 tokens

2026-10-02
359,445,648,981 tokens

2026-10-03
234,245,189,941 tokens

Jul 6, 2026Oct 3, 2026

Daily observations · 32 days

Date (UTC)	Reported tokens	Reported routes
Oct 3, 2026	234,245,189,941	1
Oct 2, 2026	359,445,648,981	1
Oct 1, 2026	337,946,027,237	1
Sep 30, 2026	365,689,306,932	1
Sep 29, 2026	330,481,407,986	1
Sep 28, 2026	302,500,473,863	1
Sep 27, 2026	224,013,060,669	1
Sep 26, 2026	231,789,605,233	1
Sep 25, 2026	340,315,765,567	1
Sep 24, 2026	312,983,002,538	1
Sep 23, 2026	310,334,451,604	1
Sep 22, 2026	391,040,911,838	1
Sep 21, 2026	345,986,100,251	1
Sep 20, 2026	254,730,762,105	1
Sep 19, 2026	237,332,736,721	1
Sep 18, 2026	271,983,234,276	1
Sep 17, 2026	327,315,493,226	1
Sep 16, 2026	389,353,011,138	1
Sep 15, 2026	414,576,677,239	1
Sep 14, 2026	298,868,541,030	1
Sep 13, 2026	200,168,978,092	1
Sep 12, 2026	227,647,146,646	1
Sep 11, 2026	268,990,059,254	1
Sep 10, 2026	363,587,380,793	1
Sep 9, 2026	652,963,426,227	1
Sep 8, 2026	565,738,446,714	1
Sep 7, 2026	276,502,500,205	1
Sep 6, 2026	205,638,900,246	1
Sep 5, 2026	216,064,543,480	1
Sep 4, 2026	317,550,771,802	1
Sep 3, 2026	273,211,217,398	1
Sep 2, 2026	55,220,179,915	1

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-3.8-flashObserved Oct 4, 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: 2026-09-02

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

Model IDgoogle/gemini-3.8-flash

Version IDgoogle/gemini-3.8-flash-20260902

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 3.8 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 3.8 Flash?

There are 33 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.

Sep 14, 2026 · 22d7055ca64f
Sep 12, 2026 · dea126055aaa