Google: 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 workflow…
google/gemini-3.1-pro-preview-20260219
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.
Specifications & capabilities
- Input
- audio, file, image, text, video
- Output
- text
- Context window · tokens
- 1048576
- Knowledge cutoff
- 2025-01
- Published model ID
- gemini-3.1-pro-preview@default
- Capabilities
- audioInput, batch, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗Evaluations
101–120 / 130
1,476.027
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality English
- dimension
- factuality
- metric
- Arena rating
- rank
- 38
- sample size
- 57099
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1472.8753011785998
- confidence upper
- 1479.177885697919
Original result ↗1,465.242
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 38
- sample size
- 45258
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1461.05616793873
- confidence upper
- 1469.4286280129024
Original result ↗1,480.148
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 39
- sample size
- 38315
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1475.7101654472176
- confidence upper
- 1484.5867829348658
Original result ↗1,469.372
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Business And Management And Financial Operations
- dimension
- factuality
- metric
- Arena rating
- rank
- 39
- sample size
- 22453
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1464.7452292479954
- confidence upper
- 1473.9988664281466
Original result ↗-0.004
- source id
- lmarena
- leaderboard name
- LMArena Agent Tool Hallucination Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 40
- sample size
- 65463
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- -0.012543998280949948
- confidence upper
- 0.005042192608147273
Original result ↗1,485.766
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 41
- sample size
- 51750
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1481.777573342364
- confidence upper
- 1489.7537070312328
Original result ↗-0.045
- source id
- lmarena
- leaderboard name
- LMArena Agent Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 41
- sample size
- 87422
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- -0.05993740731370519
- confidence upper
- -0.029996580812443933
Original result ↗1,483.463
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Longer Query
- dimension
- factuality
- metric
- Arena rating
- rank
- 42
- sample size
- 55846
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1480.2535823889912
- confidence upper
- 1486.6732678627504
Original result ↗1,490.111
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts
- dimension
- factuality
- metric
- Arena rating
- rank
- 45
- sample size
- 85644
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1487.3168187429837
- confidence upper
- 1492.904889023232
Original result ↗1,466.723
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Mathematical
- dimension
- factuality
- metric
- Arena rating
- rank
- 45
- sample size
- 6013
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1459.246909404429
- confidence upper
- 1474.199705232605
Original result ↗1,480.128
- source id
- lmarena
- leaderboard name
- LMArena Webdev Image To Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 46
- sample size
- 8052
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1471.3041514213928
- confidence upper
- 1488.9528474080262
Original result ↗1,466.336
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Instruction Following
- dimension
- factuality
- metric
- Arena rating
- rank
- 46
- sample size
- 42975
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1462.846783007752
- confidence upper
- 1469.8248314069622
Original result ↗-0.082
- source id
- lmarena
- leaderboard name
- LMArena Agent Steerability Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 46
- sample size
- 7376
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- -0.10968677389929113
- confidence upper
- -0.05490559140224907
Original result ↗1,476.257
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 47
- sample size
- 7350
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1468.4076610306197
- confidence upper
- 1484.1065734119925
Original result ↗1,483.121
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 48
- sample size
- 13535
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1477.0043932626986
- confidence upper
- 1489.2371822099453
Original result ↗1,483.062
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 48
- sample size
- 7350
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1475.2160968198666
- confidence upper
- 1490.9076514531512
Original result ↗1,495.604
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts English
- dimension
- factuality
- metric
- Arena rating
- rank
- 49
- sample size
- 35954
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1491.8136729168434
- confidence upper
- 1499.393722773286
Original result ↗-0.113
- source id
- lmarena
- leaderboard name
- LMArena Agent Task Outcome Explicit Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 50
- sample size
- 34532
- evaluated at
- 2026-11-11T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- -0.1424561559899705
- confidence upper
- -0.08348008610476901
Original result ↗1,492.363
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Expert
- dimension
- factuality
- metric
- Arena rating
- rank
- 51
- sample size
- 11359
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- 1486.4661112085246
- confidence upper
- 1498.2597645713863
Original result ↗-0.233
- source id
- lmarena
- leaderboard name
- LMArena Agent Bash Recovery Steps Overall
- dimension
- agentic
- metric
- Arena score
- rank
- 51
- sample size
- 224173
- evaluated at
- 2026-10-08T00:00:00.000Z
- source model id
- Gemini 3.1 Pro Preview
- confidence lower
- -0.2513309624549065
- confidence upper
- -0.2139733979728338
Original result ↗Published prices
1–20 / 48
$0.20
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$0.38
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_write_tokens_per_million
- Currency
- USD
$0.000002
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- image
- Currency
- USD
$2.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$12.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
$0.000001
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- image
- Currency
- USD
- Billing conditions
- mode
- batch
$1.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$6.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- mode
- batch
$0.01
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- web_search
- Currency
- USD
- Billing conditions
- mode
- batch
$0.40
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 200001
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 200001
- min_inclusive
- 0
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.20
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- service_tier
- flex
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$0.36
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- cache_read_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- service_tier
- priority
- billing_scope
- via Vercel AI Gateway
- Billing label
- Cached input / 1M
- Pricing via
- Vercel AI Gateway
$4.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 200001
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$2.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 200001
- min_inclusive
- 0
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$1.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- service_tier
- flex
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$3.60
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- service_tier
- priority
- billing_scope
- via Vercel AI Gateway
- Billing label
- Input tokens / 1M
- Pricing via
- Vercel AI Gateway
$18.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- min_inclusive
- 200001
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
$12.00
- Inference provider
- vercelAIGatewayCatalog
- Platform
- google
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing conditions
- endpoint
- google | google/gemini-3.1-pro-preview
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- context_tokens
- max_exclusive
- 200001
- min_inclusive
- 0
- Billing label
- Output tokens / 1M
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–3 / 3
- source model id
- gemini-3.1-pro-preview
- hosting
- gateway
- context length
- 1000000
- max output tokens
- 65536
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- google/gemini-3.1-pro-preview
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 64000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
- webSearch
- source model id
- publishers/google/models/gemini-3.1-pro-preview@default
- hosting
- vertex-managed
- context length
- 1048576
- max output tokens
- 65536
- capabilities
- batch
- multimodal
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- visionInput
Safety assessments
1–1 / 1
41 / 100
- source id
- stanfordFMTI
- canonical model id
- google/gemini-3.1-pro-preview-20260219
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Google
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 41 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–9 / 9
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- vertexAI
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-01
- normalized value
- 2025-01
- precision
- month
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 65536
- normalized value
- 65536
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 65536
- normalized value
- 65536
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 64000
- normalized value
- 64000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 65536
- normalized value
- 65536
- scope
- source-model
- source id
- vertexAI
- confidence
- 1
Explore more models