Skip to main content
GoogleFeb 19, 2026

Gemini 3.1 Pro Preview

gemini-3-1-pro-previewAnonymized

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

$2.50/$15.00
per 1M in / out
1M
context window
32K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 37%81.0%
Blended pricecheaper than 18%$5.63
Context windowlarger than 42%1M
Max outputlarger than 21%32K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImageVideoAudio
OutText
Streamingstream: true
Function callingtoolsStructured outputsresponse_formatReasoningreasoning_effort low · medium · highVisionUp to 20 images
Video inputVideo in messages
Audio inputAudio in messages
Web searchenable_web_search
Prompt cachingReads at $0.50

Not supportedX search and log probabilities

Benchmarks

GPQA Diamond
81.0%88th of 139 · 63 score higher for less, including GPT-6.2 Sol, GPT-6.2 Sol Pro and Gemini 4 Argon

Specs

Model ID
gemini-3-1-pro-preview
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
32,768 tokens
Reasoning
low · medium · high · default low
Precision
Set by the provider
Privacy
Anonymized
Weights
Closed
Added
Feb 19, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
Gemini 3.1 Pro Preview$2.50$15.0081.0%1M32K——
GPT-5.4$2.50$15.0089.9%1M128K——
Claude Sonnet 4.6$3.00$15.0078.8%1M64K——
GPT-5.3 Codex$1.75$14.0085.0%400K128K——
GPT-5.2$1.75$14.0089.4%256K64K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$2.50per 1M tokens
Cached input$0.5080% off input
Output$15.00per 1M tokens

Estimate a workload

$0.0125per request
$125for 10,000 requests

Blended price against similar models

Gemini 3.1 Pro Preview$5.63
GPT-5.4$5.63
GPT-5.2$4.81

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.

curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3-1-pro-preview",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "low"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelgemini-3-1-pro-previewRequired
messagestext · image_url · video_url · input_audioContent parts the model reads
max_completion_tokensUp to 32,768Counts reasoning tokens
reasoning_effortlow | medium | highDefault low
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations