Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation of the Gemini 3 series, it combines high-precision reasoning across text, image, video, audio, and code with a 1M-token context window. Reasoning Details must be preserved when using multi-turn tool calling, see our docs here: https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning. The 3.1 update introduces measurable gains in SWE benchmarks and real-world coding environments, along with stronger autonomous task execution in structured domains such as finance and spreadsheet-based workflows.

Designed for advanced development and agentic systems, Gemini 3.1 Pro Preview improves long-horizon stability and tool orchestration while increasing token efficiency. It introduces a new medium thinking level to better balance cost, speed, and performance. The model excels in agentic coding, structured planning, multimodal analysis, and workflow automation, making it well-suited for autonomous agents, financial modeling, spreadsheet automation, and high-context enterprise tasks.

google/gemini-3.1-pro-preview

Organization: Google
Family: gemini-pro
Providers: 37
Context: 1,048,576
Output limit: 65,536
Knowledge: 2025-01
Release: 2026-02-19
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.

47 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Abacus	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
AIHubMix	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
AI/ML API	google/gemini-3.1-pro-preview	1,000,000	65,536	— / —	—	—	—	View
Auriko	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Cloudflare AI Gateway	google/gemini-3.1-pro	1,000,000	65,536	— / —	—	—	—	View
CrossModel	gemini/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
DaoXE	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Databricks	databricks-gemini-3-1-pro	1,048,576	65,536	— / —	—	—	—	View
DevPass (LLM Gateway)	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Eden AI	vertex/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Eden AI	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
FastRouter	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
FrogBot	gemini-3-1-pro-preview	1,000,000	64,000	— / —	—	—	—	View
Google	gemini-pro-latest	1,048,576	65,536	— / —	—	—	—	View
Impossibl	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Kenari	gemini-3-1-pro	1,048,576	65,536	— / —	—	—	—	View
Kilo Gateway	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
LLM Gateway	google-ai-studio/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
LLM Gateway	quartz/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
LLM Gateway	google-vertex/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Merge Gateway	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.1-pro-preview-low	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
NanoGPT	google/gemini-3.1-pro-preview-high	1,048,576	65,536	— / —	—	—	—	View
Ofox	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
OpenCode	gemini-3.1-pro	1,048,576	65,536	— / —	—	—	—	View
Googlevia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$2.00 / $12.00	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$3.60 / $21.60	Yes	Yes	Yes	View
Googlevia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$1.00 / $6.00	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$1.00 / $6.00	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$3.60 / $21.60	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemini-3.1-pro-preview unknown	1,048,576	65,536	$2.00 / $12.00	Yes	Yes	Yes	View
Opper	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
OrcaRouter	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Perplexity Agent	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Poe	google/gemini-3.1-pro	1,048,576	65,536	— / —	—	—	—	View
Prime Inference	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Requesty	gemini-3.1-pro-preview	1,048,576	65,535	— / —	—	—	—	View
Snowflake Cortex	gemini-3.1-pro	1,000,000	64,000	— / —	—	—	—	View
Standard Compute	google/gemini-3.1-pro-preview	1,048,576	50,000	— / —	—	—	—	View
Tempr Gateway	google/gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Venice AI	gemini-3-1-pro-preview	1,000,000	32,768	— / —	—	—	—	View
Vercel AI Gateway	google/gemini-3.1-pro-preview	1,000,000	64,000	— / —	—	—	—	View
Vertex	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
Vivgrid	gemini-3.1-pro-preview	1,048,576	65,536	— / —	—	—	—	View
ZenMux	google/gemini-3.1-pro-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.

USD per million tokens

Input from$1.00Per 1M input tokens

Output from$6.00Per 1M output tokens

Available offers47Across 37 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

$1.00$6.00

Google AI Studiogoogle-ai-studio/flex

$1.00$6.00

Googlegoogle-vertex/global

$2.00$12.00

Google AI Studiogoogle-ai-studio

$2.00$12.00

Googlegoogle-vertex/global/priority

$3.60$21.60

Google AI Studiogoogle-ai-studio/priority

$3.60$21.60

google/gemini-3.1-pro-previewObserved Oct 10, 2026, 11:31 AM UTC

Input: $2.00
Output: $12.00
Cache read: $0.20
Cache write: $0.375

Additional fees and pricing conditions

audio: $0.000002 / audio token
image: $0.000002 / image
web search: $0.014 / search
input audio cache: $0.0000002 / audio token
internal reasoning: $0.000012 / reasoning token

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "audio": "0.000004",
    "prompt": "0.000004",
    "completion": "0.000018",
    "input_cache_read": "0.0000004",
    "input_audio_cache": "0.0000004",
    "min_prompt_tokens": 200000
  }
]

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Googlegoogle-vertex/global	$2.00	$12.00	$0.20	$0.375
Googlegoogle-vertex/global/priority	$3.60	$21.60	$0.36	$0.675
Googlegoogle-vertex/global/flex	$1.00	$6.00	$0.10	$0.1875
Google AI Studiogoogle-ai-studio/flex	$1.00	$6.00	$0.10	$0.1875
Google AI Studiogoogle-ai-studio/priority	$3.60	$21.60	$0.36	$0.675
Google AI Studiogoogle-ai-studio	$2.00	$12.00	$0.20	$0.375

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 · 5 endpoints

P50P75P90P99

Googlegoogle-vertex/global

2,845.5–13,254.96 ms

Googlegoogle-vertex/global/priority

4,557–4,557 ms

Googlegoogle-vertex/global/flex

88,016–106,935.96 ms

Google AI Studiogoogle-ai-studio/flex

3,388–9,233.92 ms

Google AI Studiogoogle-ai-studio

4,840–36,098.7 ms

All latency percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	2,845.5 ms	3,373.25 ms	4,710.9 ms	13,254.96 ms
Googlegoogle-vertex/global/priority	4,557 ms	4,557 ms	4,557 ms	4,557 ms
Googlegoogle-vertex/global/flex	88,016 ms	88,344 ms	92,096.6 ms	106,935.96 ms
Google AI Studiogoogle-ai-studio/flex	3,388 ms	3,755 ms	4,499.2 ms	9,233.92 ms
Google AI Studiogoogle-ai-studio	4,840 ms	14,189 ms	19,900 ms	36,098.7 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 5 endpoints

P50P75P90P99

Googlegoogle-vertex/global

84–135.09 t/s

Googlegoogle-vertex/global/priority

113–113 t/s

Googlegoogle-vertex/global/flex

29–70.72 t/s

Google AI Studiogoogle-ai-studio/flex

94–155.5 t/s

Google AI Studiogoogle-ai-studio

115–167 t/s

All throughput percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Googlegoogle-vertex/global	84 t/s	95 t/s	106 t/s	135.09 t/s
Googlegoogle-vertex/global/priority	113 t/s	113 t/s	113 t/s	113 t/s
Googlegoogle-vertex/global/flex	29 t/s	33 t/s	43 t/s	70.72 t/s
Google AI Studiogoogle-ai-studio/flex	94 t/s	108.25 t/s	132 t/s	155.5 t/s
Google AI Studiogoogle-ai-studio	115 t/s	139 t/s	148 t/s	167 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 10, 2026, 11:31 AM UTC

100%

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

—

100%

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

—

99.37%

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

—

100%

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

—

Google AI Studiogoogle-ai-studioObserved Oct 10, 2026, 11:31 AM UTC

100%

99.86%

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-3.1-pro-previewObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 70

Coding

68.8

Agentic

8.2

Intelligence

29.7

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,114	44.2%	22
agents	agentichtmlslides	1,226	55.8%	4
agents	agenticslides	1,112	33.8%	7
agents	agenticslides(html)	1,219	54.4%	4
agents	agenticslides(python-pptx)	1,107	33.9%	7
agents	androidnative	1,064	41.3%	34
agents	fullstack	1,069	40.8%	32
agents	godotgamedev	1,236	60%	8
agents	htmlslides	1,153	48.6%	16
agents	mobileapps	1,090	43.2%	38
agents	pptxslides	1,110	34.1%	7
agents	python-pptxslides	1,109	31.9%	25
agents	webapps	1,119	44.6%	31
models	3d	1,240	58.4%	34
models	asciiart	1,275	63.5%	11
models	codecategories	1,248	64.4%	37
models	dataviz	1,242	61.8%	34
models	gamedev	1,210	52.1%	48
models	svg	1,285	67.8%	11
models	uicomponent	1,283	69.4%	25
models	website	1,257	64.4%	37

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 3.1 Pro Preview

94.529%

tau bench verified airlineGoogle: Gemini 3.1 Pro Preview

75.778%

Evaluation	Configuration	Source	Results	Details
models · gamedev	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,204 Elo	Details
models · dataviz	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,239 Elo	Details
models · codecategories	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,244 Elo	Details
models · website	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,253 Elo	Details
models · 3d	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,224 Elo	Details
models · svg	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,285 Elo	Details
models · gamedev	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,197 Elo	Details
gpqa diamond	Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	OpenRouter	94.529%	Details
models · uicomponent	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,224 Elo	Details
models · website	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,234 Elo	Details
models · codecategories	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,231 Elo	Details
models · asciiart	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,270 Elo	Details
models · svg	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,245 Elo	Details
tau bench verified airline	Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	OpenRouter	75.778%	Details
Composite indices	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Artificial Analysis	Intelligence 29.7 · Coding 68.8 · Agentic 8.2	Details
models · uicomponent	Gemini 3 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,277 Elo	Details
models · dataviz	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,209 Elo	Details
models · 3d	Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-20260219	Design Arena	1,234 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

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

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	google/gemini-3.1-pro-preview-20260219	10–49 turns	$0.59665	Details
Hermes Agent	google/gemini-3.1-pro-preview-20260219	1 turn	$0.014543	Details
Hermes Agent	google/gemini-3.1-pro-preview-20260219	2–9 turns	$0.081262	Details

Source: OpenRouter, as of Oct 20, 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 usage1,094,590,844,760 reported tokens · 33 days with observations

77B0

2026-07-27
27,816,597,555 tokens

2026-07-28
32,918,030,979 tokens

2026-07-29
26,124,525,105 tokens

2026-07-30
27,649,481,847 tokens

2026-07-31
26,316,187,434 tokens

2026-08-01
16,952,565,452 tokens

2026-08-02
15,383,924,623 tokens

2026-08-03
23,213,511,029 tokens

2026-08-05
26,787,965,732 tokens

2026-08-06
40,011,971,008 tokens

2026-08-07
23,408,073,351 tokens

2026-08-08
15,683,908,664 tokens

2026-08-10
21,748,533,469 tokens

2026-08-11
25,862,524,172 tokens

2026-08-12
34,105,457,159 tokens

2026-08-14
36,996,583,423 tokens

2026-08-17
27,300,322,671 tokens

2026-08-18
45,151,649,166 tokens

2026-08-19
76,999,287,127 tokens

2026-08-20
45,337,328,400 tokens

2026-08-21
31,700,530,498 tokens

2026-08-22
27,651,189,927 tokens

2026-08-26
25,468,454,534 tokens

2026-08-27
40,477,223,530 tokens

2026-08-28
46,095,918,686 tokens

2026-08-29
42,831,168,645 tokens

2026-08-30
33,492,452,533 tokens

2026-08-31
25,810,065,799 tokens

2026-09-01
31,530,908,142 tokens

2026-09-02
32,253,180,313 tokens

2026-09-08
36,794,221,268 tokens

2026-09-18
54,285,004,157 tokens

2026-09-19
50,432,098,362 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 33 days

Date (UTC)	Reported tokens	Reported routes
Sep 19, 2026	50,432,098,362	1
Sep 18, 2026	54,285,004,157	1
Sep 8, 2026	36,794,221,268	1
Sep 2, 2026	32,253,180,313	1
Sep 1, 2026	31,530,908,142	1
Aug 31, 2026	25,810,065,799	1
Aug 30, 2026	33,492,452,533	1
Aug 29, 2026	42,831,168,645	1
Aug 28, 2026	46,095,918,686	1
Aug 27, 2026	40,477,223,530	1
Aug 26, 2026	25,468,454,534	1
Aug 22, 2026	27,651,189,927	1
Aug 21, 2026	31,700,530,498	1
Aug 20, 2026	45,337,328,400	1
Aug 19, 2026	76,999,287,127	1
Aug 18, 2026	45,151,649,166	1
Aug 17, 2026	27,300,322,671	1
Aug 14, 2026	36,996,583,423	1
Aug 12, 2026	34,105,457,159	1
Aug 11, 2026	25,862,524,172	1
Aug 10, 2026	21,748,533,469	1
Aug 8, 2026	15,683,908,664	1
Aug 7, 2026	23,408,073,351	1
Aug 6, 2026	40,011,971,008	1
Aug 5, 2026	26,787,965,732	1
Aug 3, 2026	23,213,511,029	1
Aug 2, 2026	15,383,924,623	1
Aug 1, 2026	16,952,565,452	1
Jul 31, 2026	26,316,187,434	1
Jul 30, 2026	27,649,481,847	1
Jul 29, 2026	26,124,525,105	1
Jul 28, 2026	32,918,030,979	1
Jul 27, 2026	27,816,597,555	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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-3.1-pro-previewObserved Oct 10, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 65,536
Tokenizer: Gemini
Input: audio, file, image, text, video
Output: text
Moderation: No
Added to OpenRouter: 2026-02-19

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

Model IDgoogle/gemini-3.1-pro-preview

Version IDgoogle/gemini-3.1-pro-preview-20260219

Reasoning

Required: Yes
Enabled by default: Not reported
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 3.1 Pro Preview cost?

Listed rates start at $1.00 per million input tokens and $6.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemini 3.1 Pro Preview?

There are 47 cataloged offers across 37 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 · b0508ff57ea3
Sep 14, 2026 · 706f9e4f07ce
Sep 12, 2026 · 42d44a6ce085