modelbenchmark.io

Gemini 3.1 Pro Preview

Google · gemini-3-1-pro

Compare

Reasoning-first Gemini preview for agentic coding and complex problem solving

Specification

google listing

Context
1M
Max output
66K
Released
2026-02-19
Knowledge cutoff
2025-01
Retires
Open weights
no
Input
text, image, video, audio, pdf
Output
text

Price

US dollars per million tokens · google list price

Input
$2.00
Output
$12.00
Cache read
$0.20
Cache write
$0.375

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputvertex_ai-language-models$1.00
Batch outputvertex_ai-language-models$6.00
Priority inputvertex_ai-language-models$3.60
Priority outputvertex_ai-language-models$21.60

Batch input is 50% below the interactive input price at the same listing.

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.40
200KCache write$0.25
200KInput$4.00
200KOutput$18.00

Rate limits

as listed

Requests per minute
2,000
Tokens per minute
800,000

Quality

12 benchmarks · 2 sources

Composite
86th
percentile of 334 scored models
Rank
48 / 334
±0.06 sd
Evidence
12 × 2
3 or more benchmarks, from 2 or more sources
Effort range
2.7
points between effort settings
coding18th1/3 bench
reasoning92nd4/4 bench
math85th5/7 bench
knowledge99th1/1 bench
general68th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high92nd7
medium88th1
low83rd1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Chess Puzzles55.0 ±5.0defaultEpoch AI2026-02-19
49.0 ±5.0highEpoch AI2026-08-06
Settings differ by 6.0 points on this benchmark.
SimpleQA Verified73.5 ±1.4highEpoch AI2026-08-10
FrontierMath-v162.9 ±2.8default · 2 runsEpoch AI2026-02-19
GPQA diamond94.4 ±1.6highEpoch AI2026-08-06
94.1 ±1.7defaultEpoch AI2026-02-20
Settings differ by 0.3 points on this benchmark.
OTIS Mock AIME 2024-202595.6 ±3.1defaultEpoch AI2026-02-20
95.6 ±3.1highEpoch AI2026-08-06
Mystery Game Puzzles34.0 ±4.8highEpoch AI2026-07-27
32.0 ±4.7mediumEpoch AI2026-08-06
29.0 ±4.6lowEpoch AI2026-08-06
Settings differ by 5.0 points on this benchmark.
FrontierMath-Tiers-1-3-v259.6 ±2.9defaultEpoch AI2026-06-11
LiveBench78.0high · 23 runsLiveBench2026-06-25
FrontierMath-Tier-4-2025-07-018.3 ±5.4default · 2 runsEpoch AI2026-02-19
FrontierMath-Tier-4-v226.8 ±7.0defaultEpoch AI2026-06-11
EBR-bench14.3defaultEpoch AI2026-06-25
MirrorCode8.9 ±4.6highEpoch AI2026-08-10

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 41 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$2.00$12.00$0.201M66K
kenarifreefree1M66K
kilo$1.00$6.00$0.10$0.18751M66K
302ai$2.00$12.001M66K
abacus$2.00$12.00$0.201M66K
aihubmix$2.00$12.00$0.201M66K
auriko$2.00$12.00$0.201M66K
crossmodel$2.00$12.00$0.20$2.001M66K
daoxe$2.00$12.00$0.201M66K
databricks
$2.00
$2.50
$12.00
$15.00
$0.20
$0.25
$2.501M66K
deepinfra$2.00$12.001M
edenai$2.00$12.00$0.20$0.3751M66K
fastrouter$2.00$12.001M66K
frogbot$2.00$12.00$0.201M64K
gemini$2.00$12.00$0.201M66K
google-vertex$2.00$12.00$0.201M66K
impossibl$2.00$12.00$0.201M66K
llmgateway$2.00$12.00$0.201M66K
llmgateway-providers · google-ai-studio$2.00$12.00$0.201M66K
llmgateway-providers · google-vertex$2.00$12.00$0.201M66K
llmgateway-providers · quartz$2.00$12.00$0.201M66K
merge-gateway$2.00$12.00$0.201M66K
nano-gpt$2.00$12.00$0.20$0.3751M66K
neon$2.00$12.00$0.201M66K
ofox$2.00$12.00$0.20$4.501M66K
opencode$2.00$12.00$0.201M66K
openrouter$2.00$12.00$0.20$0.3751M66K
opper$2.00$12.00$0.201M66K
orcarouter$2.00$12.00$0.201M66K
perplexity$2.00$12.00$0.20
perplexity-agent$2.00$12.00$0.201M66K
pioneer$2.00$12.00$0.20$0.3751M64K
poe$2.00$12.00$0.201M66K
requesty$2.00$12.00$0.20$4.501M66K
vercel$2.00$12.00$0.201M64K
vertex_ai$2.00$12.00$0.201M66K
vertex_ai-language-models$2.00$12.00$0.201M66K
vivgrid$2.00$12.00$0.201M66K
zenmux$2.00$12.00$0.20$4.501M64K
venice$2.50$15.00$0.50$0.501M33K
snowflake-cortex1M66K

More from Google

most-hosted first