Skip to content
Seedance 2.0 Face is here — generate video from real-person reference photos.Try it now →
Back to Models
googlegoogle·Feb 19, 2026

Google: Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview
context
1.0M
Max Output
65.5K
Input / 1M
$2.00
Output / 1M
$12.00

About

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 reasoning across text, image, video, audio, and code with a 1M-token context window. The 3.1 update introduces 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. It introduces a new medium thinking level to balance cost, speed, and performance, and is suited to agentic coding, structured planning, multimodal analysis, and workflow automation.

Capabilities

Context Length
1.0M
Max Output
65.5K
Reasoning
Yes
In
audio, file, image, text, video
Out
text

Benchmarks

View leaderboard
46.5#13 of 133
Intelligence Index
55.5#5 of 118
Coding Index

Reasoning & Knowledge

GPQA Diamond94.1%
HLE44.7%

Coding & Agentic

SciCode58.9%
Terminal-Bench Hard53.8%

Source: Artificial Analysis

Pricing

Full pricing
Type≤200K>200K
Input$2.00$4.00
Output$12.00$18.00
Cache Read$0.20$0.40
Cache Write$0.375$0.375
Audio Input$2.00$4.00
Audio Cache$0.20$0.40
Reasoning$12.00
Image Input$2.00
Web Search$0.01 / call

API

API reference

OpenAI-compatible · Model ID google/gemini-3.1-pro-preview

curl https://api.elliotgate.com/v1/chat/completions \
  -H "Authorization: Bearer sk-omg-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.1-pro-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OFTEN COMPARED

Gemini 3.1 Pro Preview comparisons

Decide which model wins on the dimensions that matter for your workload — context, benchmarks, pricing, or serving latency.