Singularity Logs

THE MODEL, IN DETAIL / Google

Gemini 3.1 Pro Preview

google/gemini-3.1-pro-previewProprietaryReasoning

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...

OpenRouter
Source-linked model intelligenceCatalog added 19 Feb 2026Specifications observed 16 Oct 2026

Overall agents

#41

Arena agent score

Context window

1M

65.5K max output tokens

Input price

$2

USD / million input tokens

Output price

$12

USD / million output tokens

Inference providers

2

6 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

At least three published accuracy scores are needed for this view.

In good company

Overall agents · Arena · official dataset

17.2
Anthropic
14.8
OpenAI
14.1
Anthropic
13.7
Google
13.7
OpenAI
12.5
Anthropic
11.2
OpenAI
9.2
Anthropic
8.4
Anthropic
7.4
OpenAI

54 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

0published results
0 evaluation sources
ReasoningAwaiting evidence
CodingAwaiting evidence
MathematicsAwaiting evidence
VisionAwaiting evidence
AgenticAwaiting evidence
Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

Where people rank it

Published rankings for this exact model or configuration. Each source keeps its original metric.

Overall agentsArena agent score · 14 Oct 2026#41-3.5%Confidence interval: -4.9–-2.2Agents for workTask-outcome score · 14 Oct 2026#47-10.1%Confidence interval: -12.5–-7.7

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

0 published results

Percentage-based evaluations will appear here when published.

0 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Artificial Analysis indices

Published in the OpenRouter catalog · source-defined index values

Coding Index68.8
Agentic Index8.2
Intelligence Index29.7

Catalog observation: 16 Oct 2026. Index versions and evaluation settings are not supplied in this feed. These are not Singularity composite scores.

Artificial Analysis

Design Arena

Source-reported Elo across individual design categories

Agenticgamedev1,114
agents arena · Rank #22 · 44.2% win rate
Agentichtmlslides1,226
agents arena · Rank #4 · 55.8% win rate
Agenticslides1,112
agents arena · Rank #7 · 33.8% win rate
Agenticslides(Html)1,219
agents arena · Rank #4 · 54.4% win rate
Agenticslides(Python-Pptx)1,107
agents arena · Rank #7 · 33.9% win rate
Androidnative1,064
agents arena · Rank #34 · 41.4% win rate
Fullstack1,068
agents arena · Rank #32 · 40.8% win rate
Godotgamedev1,236
agents arena · Rank #8 · 60% win rate
Htmlslides1,153
agents arena · Rank #16 · 48.6% win rate
Mobileapps1,091
agents arena · Rank #37 · 43.2% win rate
Pptxslides1,110
agents arena · Rank #7 · 34.1% win rate
Python-Pptxslides1,109
agents arena · Rank #25 · 31.9% win rate
Webapps1,119
agents arena · Rank #31 · 44.6% win rate
3d1,235
models arena · Rank #39 · 58.4% win rate
Asciiart1,272
models arena · Rank #11 · 63.5% win rate
Codecategories1,245
models arena · Rank #42 · 64.4% win rate
Dataviz1,240
models arena · Rank #38 · 61.8% win rate
Gamedev1,206
models arena · Rank #51 · 52.1% win rate
Svg1,285
models arena · Rank #11 · 67.8% win rate
Uicomponent1,279
models arena · Rank #26 · 69.4% win rate
Website1,254
models arena · Rank #40 · 64.4% win rate

Catalog observation: 16 Oct 2026. Category ratings have separate comparison pools.

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$2per million tokens
Output$12per million tokens
Cache read$0.2per million tokens
Cache write$0.375per million tokens
Additional published rates
Additional rates supplied by the model catalog
Billing fieldPublished rateBilling basis
Audio$0.000002Source-supplied USD rate; see provider billing terms
Image$0.000002Source-supplied USD rate; see provider billing terms
Overrides[{"audio":"0.000004","prompt":"0.000004","completion":"0.000018","input_cache_read":"0.0000004","input_audio_cache":"0.0000004","min_prompt_tokens":200000}]Source-supplied USD rate; see provider billing terms
Web Search$0.014Source-supplied USD rate; see provider billing terms
Input Audio Cache$0.0000002Source-supplied USD rate; see provider billing terms
Input Cache Write$0.375USD / million tokens
Internal Reasoning$12USD / million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

$32estimated total
Uncached input$20
Cached input$0
Output$12
Per request$0.032
Without cache discount$32
Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

2 providers · 6 routes
Provider routes for Gemini 3.1 Pro Preview, observed 16 Oct 2026
Provider / routeInput / MOutput / MCache / MContextOutput limitSpeedLatencyAvailability · 1dRates
GGoogleQuantization not disclosed · flex$1$6$0.11M65.5K——91%
GGoogle AI StudioQuantization not disclosed · flex$1$6$0.11M65.5K——100%
GGoogleQuantization not disclosed$2$12$0.21M65.5K——100%
GGoogle AI StudioQuantization not disclosed$2$12$0.21M65.5K——99.93%
GGoogleQuantization not disclosed · priority$3.6$21.6$0.361M65.5K——100%
GGoogle AI StudioQuantization not disclosed · priority$3.6$21.6$0.361M65.5K———

Snapshot observed 16 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput
Google · flex
Input
$1
Output
$6
Google AI Studio · flex
Input
$1
Output
$6
Google
Input
$2
Output
$12
Google AI Studio
Input
$2
Output
$12
Google · priority
Input
$3.6
Output
$21.6
Google AI Studio · priority
Input
$3.6
Output
$21.6

Reported availability

Provider availability over the selected observation window

Google · flex91%
Google AI Studio · flex100%
Google100%
Google AI Studio99.93%
Google · priority100%
Google AI Studio · priority—

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

Google · flex1M
Google AI Studio · flex1M
Google1M
Google AI Studio1M
Google · priority1M
Google AI Studio · priority1M

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

AudioFileImageTextVideo
Gemini 3.1 Pro PreviewReasoning supported

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningSupported
Tool callingSupported
Tool choiceSupported
Structured outputsSupported
Response formatSupported
Reasoning detailsSupported
Seed controlSupported
Stop sequencesSupported
Prompt cachingSupported
TemperatureSupported

Room to work

Context capacity and completion limits

1Mtotal context tokens
Context window
65.5Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context
1,048,576 tokens
Maximum output
65,536 tokens
Top-provider context
1,048,576 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider routeReasoningToolsStructured outputResponse formatImplicit caching
Google · flexSupportedSupportedSupportedSupportedNot listed
Google AI Studio · flexSupportedSupportedSupportedSupportedNot listed
GoogleSupportedSupportedSupportedSupportedNot listed
Google AI StudioSupportedSupportedSupportedSupportedNot listed
Google · prioritySupportedSupportedSupportedSupportedNot listed
Google AI Studio · prioritySupportedSupportedSupportedSupportedNot listed

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer
Google
Exact identity
Gemini 3.1 Pro Preview
Subject
Agent System
Access
proprietary
License
Proprietary
Parameters
Not disclosed
Tokenizer
Gemini
Instruction format
Not disclosed

Reasoning & controls

Reasoning
Supported
Mandatory reasoning
Yes
Reasoning by default
Not documented
Published configuration
Not disclosed
Supported reasoning efforts
high, medium, low
Default reasoning effort
medium
API parameters
12
Provider moderation
No
Quantization variants
Not disclosed

Dates & limits

Catalog added
19 Feb 2026
Knowledge cutoff
Not disclosed
Catalog expiration
Not documented
Specifications observed
16 Oct 2026
Providers observed
16 Oct 2026
Request limits
Provider-specific / not supplied
Canonical catalog ID
google/gemini-3.1-pro-preview-20260219

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

include_reasoningSupported · default not supplied
max_tokensSupported · default not supplied
reasoningSupported · default not supplied
reasoning_effortSupported · default not supplied
response_formatSupported · default not supplied
seedSupported · default not supplied
stopSupported · default not supplied
structured_outputsSupported · default not supplied
temperatureSupported · default not supplied
tool_choiceSupported · default not supplied
toolsSupported · default not supplied
top_pSupported · default not supplied
top_kDefault setting
presence_penaltyDefault setting
frequency_penaltyDefault setting
repetition_penaltyDefault setting

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "google/gemini-3.1-pro-preview",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ]
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The observation trail

Recorded events, in chronological order

Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

Model specifications observed

Catalog pricing, limits, and supported parameters captured.

Provider routes observed

6 inference routes in this snapshot.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

No published benchmark observations for this selection. Published preference rankings appear separately above.

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does Gemini 3.1 Pro Preview cost?

Catalog starting rates are $2 per million input tokens and $12 per million output tokens. Cache-read pricing is $0.2 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

1,048,576 tokens in the catalog context window. The catalog lists a maximum of 65,536 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 16 Oct 2026. Provider routes were observed on 16 Oct 2026. Missing measurements are not estimated or treated as zero.

KEEP EXPLORING

More from Google.

Explore related identities from the same developer, or take them into a side-by-side comparison.

THE RIGHT MODEL STARTS WITH THE RIGHT CONTEXT.

Put the details side by side.

Explore the trade-offs in a direct model comparison.

Compare Gemini 3.1 Pro Preview
Source-backed evidence. Different tasks. A clearer picture.
AboutMethodologyBenchmark dashboard
Gemini 3.1 Pro Preview — Singularity Logs