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 inputdatabricks$4.50
Priority inputvertex_ai-language-models$3.60
Priority outputdatabricks$27.00
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$0.50
200KCache write$0.25
200KInput$5.00
200KOutput$22.50

Rate limits

as listed

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

Quality

13 benchmarks · 2 sources

Composite
77th
percentile of 344 scored models
Rank
80 / 344
±0.06 sd
Evidence
13 × 2
3 or more benchmarks, from 2 or more sources
Effort range
0.3
points between effort settings
coding16th1/3 bench
reasoning80th4/4 bench
math81st5/7 bench
knowledge96th1/1 bench
general65th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high84th8
medium81st1
low71st1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
FrontierMath-v162.9 ±2.8default · 2 runsEpoch AI2026-02-19
SimpleQA Verified73.5 ±1.4highEpoch AI2026-08-10
GPQA diamond94.4 ±1.6highEpoch AI2026-08-06
↳94.1 ±1.7defaultEpoch AI2026-02-20
Settings differ by 0.3 points on this benchmark.
Chess Puzzles51.0 ±5.0highEpoch AI2026-10-13
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.
LiveBench78.0high · 23 runsLiveBench2026-06-25
FrontierMath-Tiers-1-3-v259.6 ±2.9defaultEpoch AI2026-06-11
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
Furniture Assembly26.7 ±5.6highEpoch AI2026-09-10
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 47 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$2.00$12.00$0.20—1M66K—
kilo$1.00$6.00$0.10$0.18751M66K—
kenari$1.20$7.1429$0.12$0.22291M66K—
302ai$2.00$12.00——1M66K—
abacus$2.00$12.00$0.20—1M66K—
aihubmix$2.00$12.00$0.20—1M66K—
aihubmix · aihubmix$2.00$12.00$0.20—1M66K—
aimlapi$2.00$12.00$0.50—1M66K—
auriko$2.00$12.00$0.20—1M66K—
cloudflare-ai-gateway$2.00$12.00$0.20—1M66K—
crossmodel$2.00$12.00$0.20$2.001M66K—
daoxe$2.00$12.00$0.20—1M66K—
databricks
$2.00
$2.50
$12.00
$15.00
$0.20
$0.25
$2.501M66K—
deepinfra$2.00$12.00——1M1M—
edenai$2.00$12.00$0.20$0.3751M66K—
fastrouter$2.00$12.00$0.20—1M66K—
frogbot$2.00$12.00$0.20—1M64K—
gemini$2.00$12.00$0.20—1M66K—
google-vertex$2.00$12.00$0.20—1M66K—
impossibl$2.00$12.00$0.20—1M66K—
llmgateway$2.00$12.00$0.20—1M66K—
llmgateway-providers · google-ai-studio$2.00$12.00$0.20—1M66K—
llmgateway-providers · google-vertex$2.00$12.00$0.20—1M66K—
llmgateway-providers · quartz$2.00$12.00$0.20—1M66K—
merge-gateway$2.00$12.00$0.20—1M66K—
nano-gpt$2.00$12.00$0.20$0.3751M66K—
neon$2.00$12.00$0.20—1M66K—
ofox$2.00$12.00$0.20$4.501M66K—
opencode$2.00$12.00$0.20—1M66K—
openrouter$2.00$12.00$0.20$0.3751M66K—
opper$2.00$12.00$0.20—1M66K—
orcarouter$2.00$12.00$0.20—1M66K—
perplexity$2.00$12.00$0.20————
perplexity-agent$2.00$12.00$0.20—1M66K—
prime$2.00$12.00——1M66K—
requesty$2.00$12.00$0.20$4.501M66K—
standardcompute$2.00$12.00$0.20$0.3751M50K—
tempr$2.00$12.00$0.20—1M66K—
vercel$2.00$12.00$0.20—1M64K—
vertex_ai$2.00$12.00$0.20—1M66K—
vertex_ai-language-models$2.00$12.00$0.20—1M66K—
zenmux$2.00$12.00$0.20—1M66K—
poe$2.0202$12.1212$0.202—1M66K—
venice$2.50$15.00$0.50$0.501M33K—
kyma · kyma$2.70$16.20$0.27—1M66K—
vivgrid$3.00$12.00$0.30—1M66K—
snowflake-cortex————1M64K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.20
2026-10-10openrouterCache read$0.20
2026-09-02poeCache read$0.20
2026-10-15poeCache read$0.202
2026-09-02vivgridCache read$0.20
2026-10-22vivgridCache read$0.30
2026-09-02openrouterCache write$0.375
2026-09-19openrouterCache write$0.375
2026-10-10openrouterCache write$0.375
2026-09-02kenariInputfree
2026-10-22kenariInput$1.20
2026-09-02openrouterInput$2.00
2026-10-10openrouterInput$2.00
2026-09-02poeInput$2.00
2026-10-15poeInput$2.0202
2026-09-02vivgridInput$2.00
2026-10-22vivgridInput$3.00
2026-09-02kenariOutputfree
2026-10-22kenariOutput$7.1429
2026-09-02openrouterOutput$12.00
2026-10-10openrouterOutput$12.00
2026-09-02poeOutput$12.00
2026-10-15poeOutput$12.1212
2026-10-13aimlapiCache read$0.65
2026-10-23aimlapiCache read$0.50
2026-10-13aimlapiInput$2.60
2026-10-23aimlapiInput$2.00
2026-10-13aimlapiOutput$15.60
2026-10-23aimlapiOutput$12.00

More from Google

most-hosted first