modelbenchmark.io

Gemini 3 Flash Preview

Google · gemini-3-flash

Compare

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Specification

google listing

Context
1M
Max output
66K
Released
2025-12-17
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
$0.50
Output
$3.00
Cache read
$0.05
Cache write
$0.0833

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputvertex_ai$0.25
Batch outputvertex_ai$1.50
Priority inputdatabricks$1.125
Priority inputvertex_ai$0.90
Priority outputdatabricks$6.75
Priority outputvertex_ai$5.40

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

Rate limits

as listed

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

Quality

10 benchmarks · 2 sources

Composite
81st
percentile of 344 scored models
Rank
66 / 344
±0.05 sd
Evidence
10 × 2
3 or more benchmarks, from 2 or more sources
Effort range
4.4
points between effort settings
coding82nd1/3 bench
reasoning79th3/4 bench
math67th5/7 bench
knowledge88th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high89th6
low64th1
minimal61st1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SimpleQA Verified66.8 ±1.5highEpoch AI2026-08-27
FrontierMath-v147.8 ±16.3default · 2 runsEpoch AI2025-12-17
OTIS Mock AIME 2024-202595.6 ±3.1highEpoch AI2026-08-06
↳92.8 ±3.5defaultEpoch AI2025-12-17
Settings differ by 2.8 points on this benchmark.
SWE-Bench verified75.8high · mini-SWE-agentSWE-bench—
↳75.4 ±2.0defaultEpoch AI2026-02-18
Sources and settings disagree by 0.4 points. Both figures stand.
GPQA diamond89.4 ±2.2highEpoch AI2026-08-06
↳83.2 ±1.9defaultEpoch AI2025-12-17
Settings differ by 6.2 points on this benchmark.
Chess Puzzles39.0 ±4.9highEpoch AI2026-10-13
FrontierMath-Tiers-1-3-v251.2 ±3.0defaultEpoch AI2026-06-11
Mystery Game Puzzles26.0 ±4.4lowEpoch AI2026-08-05
↳25.0 ±4.4minimalEpoch AI2026-08-05
↳20.0 ±4.0highEpoch AI2026-08-05
Settings differ by 6.0 points on this benchmark.
FrontierMath-Tier-4-2025-07-012.1 ±2.9default · 2 runsEpoch AI2025-12-17
FrontierMath-Tier-4-v217.1 ±5.9defaultEpoch AI2026-06-11

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

Available from 39 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$0.50$3.00$0.05—1M66K—
qihang-ai$0.07$0.43——1M66K—
kilo$0.25$1.50$0.025$0.04171M66K—
poe$0.404$2.4242$0.0404—1M66K—
jiekou$0.475$2.85$0.0475—1M66K—
302ai$0.50$3.00——1M66K—
abacus$0.50$3.00$0.05—1M66K—
aihubmix$0.50$3.00$0.05—1M66K—
aihubmix · aihubmix$0.50$3.00$0.05—1M66K—
cloudflare-ai-gateway$0.50$3.00$0.05—1M66K—
crossmodel$0.50$3.00$0.05$0.501M66K—
databricks
$0.50
$0.625
$3.00
$3.75
$0.05
$0.0625
$0.6251M66K—
edenai$0.50$3.00$0.05$0.08331M66K—
frogbot$0.50$3.00$0.05—1M66K—
gemini$0.50$3.00$0.05—1M66K—
gmi · gmi$0.50$3.00——1M66K—
google-vertex$0.50$3.00$0.05—1M66K—
llmgateway$0.50$3.00$0.05—1M66K—
llmgateway-providers · google-ai-studio$0.50$3.00$0.05—1M66K—
llmgateway-providers · google-vertex$0.50$3.00$0.05—1M66K—
merge-gateway$0.50$3.00$0.05—1M66K—
nano-gpt$0.50$3.00$0.05—1M66K—
neon$0.50$3.00$0.05—1M66K—
ofox$0.50$3.00$0.05$1.001M66K—
opencode$0.50$3.00$0.05—1M66K—
openrouter$0.50$3.00$0.05$0.08331M66K—
opper$0.50$3.00$0.05—1M66K—
orcarouter$0.50$3.00$0.05—1M66K—
perplexity$0.50$3.00$0.05————
perplexity-agent$0.50$3.00$0.05—1M66K—
prime$0.50$3.00——1M66K—
tempr$0.50$3.00$0.05—1M66K—
vercel$0.50$3.00$0.05—1M65K—
vertex_ai$0.50$3.00$0.05—1M66K—
vertex_ai-language-models$0.50$3.00$0.05—1M66K—
zenmux$0.50$3.00$0.05$1.001M66K—
kyma · kyma$0.675$4.05$0.0675—1M8K—
venice$0.70$3.75$0.07—256K66K—
anyapi————1M66K—

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.05
2026-10-10openrouterCache read$0.05
2026-09-02poeCache read$0.04
2026-10-15poeCache read$0.0404
2026-09-02openrouterCache write$0.0833
2026-09-19openrouterCache write$0.0833
2026-10-10openrouterCache write$0.0833
2026-09-02jiekouInput$0.50
2026-10-22jiekouInput$0.475
2026-09-02openrouterInput$0.50
2026-10-10openrouterInput$0.50
2026-09-02poeInput$0.40
2026-10-15poeInput$0.404
2026-09-02jiekouOutput$3.00
2026-10-22jiekouOutput$2.85
2026-09-02openrouterOutput$3.00
2026-10-10openrouterOutput$3.00
2026-09-02poeOutput$2.40
2026-10-15poeOutput$2.4242

More from Google

most-hosted first