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

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

-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 ↗

LMArena

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 ↗

LMArena

-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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

-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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

-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 ↗

LMArena

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 ↗

LMArena

-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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

google/gemini-3.1-pro-preview ↗

$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

gemini-3.1-pro-preview ↗

source model id
gemini-3.1-pro-preview
hosting
gateway
platforms
  • Cheaper Inference
context length
1000000
max output tokens
65536
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Gemini 3.1 Pro Preview ↗

source model id
google/gemini-3.1-pro-preview
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
64000
architecture
input_modalities
  • text
  • image
  • pdf
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Gemini 3.1 Pro ↗

source model id
publishers/google/models/gemini-3.1-pro-preview@default
hosting
vertex-managed
platforms
  • Google Cloud Vertex AI
context length
1048576
max output tokens
65536
architecture
input_modalities
  • audio
  • image
  • text
  • video
output_modalities
  • text
capabilities
  • batch
  • multimodal
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

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

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
1000000
normalized value
1000000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

vertexAI ↗

field
context_length
value
1048576
normalized value
1048576
scope
source-model
source id
vertexAI
confidence
1

vercelAIGatewayCatalog ↗

field
knowledge_cutoff
reported field
knowledge_cutoff
value
2025-01
normalized value
2025-01
precision
month
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

openRouter ↗

field
max_output_tokens
value
65536
normalized value
65536
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
65536
normalized value
65536
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
64000
normalized value
64000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

vertexAI ↗

field
max_output_tokens
value
65536
normalized value
65536
scope
source-model
source id
vertexAI
confidence
1

Original sources

1–12 / 12

Google Cloud · Model page ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

Google Cloud · Documentation ↗

api.cheaperinference.com · Source snapshot ↗

GitHub · Catalog ↗

Google Cloud · Catalog ↗

LMArena · Catalog ↗

OpenRouter · Catalog ↗

OpenRouter · Catalog ↗

Vercel AI Gateway · Catalog ↗

Source links

1–8 / 8

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace