VENICE ATLAS · MODEL DOSSIER · GEMINI 3.1 PRO PREVIEW

Model overview

Gemini 3.1 Pro Preview

Name: Gemini 3.1 Pro Preview
Brand: venice.ai
Price: 2.5000 USD
Availability: InStock

Gemini 3.1 Pro is the latest evolution of Google flagship frontier model with 1M context, advancing high-precision multimodal reasoning across text, image, and code.

gemini-3-1-pro-preview · venice.ai

Text · Venice catalog$2.50 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$2.50 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks20Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Biology#141.59 rating Chemistry#141.87 rating Vision#2631.28 rating Frontend Development#729.22 rating Language#732.82 rating Math#442.32 rating Physics#141.87 rating Reasoning#3444.92 rating Search#1125.04 rating Spatial Reasoning#1625.04 rating Tool Calling#3522.88 rating

Agents2 results

Finance Agent v2finance-agent-v2 · agents

43.0%

ReportedOct 2026

t2-bencht2-bench · agents

99.3%

ReportedOct 2026

Coding2 results

DeepSWE 1.1deepswe-1.1 · code

12.0%

ReportedOct 2026

FrontierSWEfrontierswe · code

40.0%

ReportedOct 2026

Language1 result

MMMLUmmmlu · language

92.6%

ReportedOct 2026

Legal1 result

Legal Agent Benchmarklegal-agent-benchmark · legal

0.00%

ReportedOct 2026

Long Context1 result

MRCR v2 (8-needle)mrcr-v2-(8-needle) · long_context

26.3%

ReportedOct 2026

Math1 result

LiveBenchlivebench · math

79.9%

ReportedOct 2026

Reasoning11 results

APEX-Agentsapex-agents · reasoning

33.5%

ReportedOct 2026

ARC-AGI v2arc-agi-v2 · reasoning

77.1%

ReportedOct 2026

BrowseCompbrowsecomp · reasoning

85.9%

ReportedOct 2026

GPQAgpqa · reasoning

94.3%

ReportedOct 2026

Humanity's Last Examhumanity's-last-exam · reasoning

51.4%

ReportedOct 2026

LiveCodeBench Prolivecodebench-pro · reasoning

96.2%

ReportedOct 2026

MCP Atlasmcp-atlas · reasoning

69.2%

ReportedOct 2026

SciCodescicode · reasoning

59.0%

ReportedOct 2026

SWE-Bench Proswe-bench-pro · reasoning

54.2%

ReportedOct 2026

SWE-Bench Verifiedswe-bench-verified · reasoning

80.6%

ReportedOct 2026

Terminal-Bench 2.0terminal-bench-2 · reasoning

68.5%

ReportedOct 2026

Vision1 result

MMMU-Prommmu-pro · vision

80.5%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $2.50
Output price per 1M tokens: $15.00
Cache read price per 1M tokens: $0.50
Cache write price per 1M tokens: $0.50
Blended price per 1M tokens (50/50): $8.75

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionAudio inputVideo inputWeb search

Endpoint metadata

Privacy: anonymized
Quantization: not-available
Maximum completion tokens: 33K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 20
Quantization: not-available
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: No
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: Yes
Supports Video Input: Yes
Default Reasoning Effort: low
Reasoning Effort Options: low, medium, high
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from google

gemini-3-8-flashGemini 3.8 Flash$0.94 input per 1M tokens ↗gemini-4-argonGemini 4 Argon$2.50 input per 1M tokens ↗google-gemma-3-27b-itGoogle Gemma 3 27B Instruct$0.12 input per 1M tokens ↗